tag:blogger.com,1999:blog-38288614463103854652024-03-05T19:38:05.866-05:00Science JonThis blog mostly summarizes useful science I read, and promotes my own research. Content posted here is my own and does not reflect the opinions of my employer or anyone else. I tweet at @sciencejon and my bio is at http://fish.freeshell.org/bio.htmlJonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.comBlogger155125tag:blogger.com,1999:blog-3828861446310385465.post-49189873413444824582024-03-01T08:03:00.001-05:002024-03-01T08:03:00.130-05:00March 2024 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/53474734303/in/datetaken/" title="Shift"><img alt="Shift" height="225" src="https://live.staticflickr.com/65535/53474734303_8429c9d2c9_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script><p>Howdy,</p><p><br />This month I have two articles on wildlife connectivity, one on global groundwater depletion, one on scientific reproducibility, and one on organizational behavior change.<br /><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a data-cke-saved-href="http://eepurl.com/diB0nr" href="http://eepurl.com/diB0nr">http://b</a><a data-cke-saved-href="http://bit.ly/sciencejon" href="http://bit.ly/sciencejon" target="_blank">it.ly/sciencejon</a> (no need to email me).<br /><br /><strong>SCIENTIFIC REPRODUCIBILITY / EVIDENCE ASSESSMENTS:</strong><br />Scientists often complain policy makers don't follow our recommendations (or even read them). But Brisco et al. 2023 finds that recommendations from meta-analyses tend to change over time as research continues. They looked at 79 papers (121 meta-analyses) and found that over time 93% of analyses either had a big change in effect size (+- 50% or more, see Fig 2 for examples) or change in statistical significance (see Fig 3). The key results are in Fig 5, which I find pretty confusing. Results staying consistently statistically significant w/ each study is rare, and ~25% of analyses showed a reversal in effect (from positive to negative or vice versa). Those reversals are the change we care the most about since it means action can backfire. BUT if you ignore the studies that were never statistically significant (seems safe) it's only 12% of analyses that flip, and if you also ignore the ones that lost significance (meaning the reversal is less meaningful) it goes down to 11%. That's still pretty bad though - 1 time out of 9 the scientific recommendation might lead to the opposite outcome we intend. They recommend scientists use cumulative meta-analyses to look for trends, and the reminder that we're often wrong reinforces the need for adaptive management and an empirical approach to seeing what works in a given context.<br /><br /><br /><strong>FRESHWATER / GROUNDWATER</strong>:<br />Jasechko et al. 2024 is a global assessment of groundwater levels since 2000 (using 170,000 wells and 1,700 aquifers) and comparing them to earlier trends for ~1/3 of those aquifers. They found 36% of aquifers were drying up (water level dropping deeper by 0.1 m / yr or more), and 6% of aquifers were improving (water level rising 0.1 m / yr or more), w/ 58% of aquifers not changing quickly in this century. 30% of the aquifers where they had 40 years of data declined faster in the 21st century than the 20 years prior (see Fig 3), but in 49% of those aquifers declines slowed or reversed. Unsurprisingly the trend is worst in drylands w/ farmland, and groundwater deepening is globally correlated w/ low precipitation, high evapotranspiration, and extent of agriculture. See Fig 1 and 2 for global map of trends, highlighting hotpsots of decline in CA, the US high plains, Iran, India, central Chile, and a few others. There's a news article about the study at https://www.cnn.com/2024/01/24/climate/groundwater-global-study-scn/index.html<br /><br /><br /><strong>WILDLIFE CONNECTIVITY:</strong><br />Iverson et al. 2024 cautions against assuming that modeled wildlife corridors connecting habitat patches ('linkages') actually receive much heavier use by wildlife. They looked at five linkage models in CA (see Fig 1), and compared them to 1) wildlife-vehicle collisions and 2) modeled wildlife presence (from a large set of wildlife observations). While black bear and puma vehicle collisions were slightly more likely in linkages, racoon collisions were LESS likely in linkages, and the other five species assessed were mixed depending on model. Across all eight species no model did consistently well for either wildlife vehicle collisions nor modeled occupancy. The authors note that the linkage models were all built on human disturbance metrics, but that another study found those metrics only significantly drove away about 1/3 of mammal species studied (including big carnivores and omnivores). Since wildlife don't have apps to find optimal travel routes, it's not shocking that they're not heavily using linkages. But this study is a good reminder to be wary of relying on models for citing narrow corridors, and it's a safer bet to assume wildlife presence is not typically highly concentrated.<br /><br />Thurman et al. 2024 argues that it's important to consider disease when doing conservation planning and wildlife management. One key point is that in some cases improving connectivity can be net harmful for some species. The case of prairie dogs and black-footed ferrets on the top of page 3 is fairly compelling (the impact of plague is high enough that mitigating its spread should be a priority). Overall, I think it's fair to say that species and ecosystems need climate-resilient connectivity options to adapt to climate change, even if increased disease transmission offsets the benefits somewhat. But thinking about disease and if/how to incorporate it in planning should always be a good idea. I like the orange questions in Figure 1, but found the longer list in Table 1 to be overwhelming (which could make it harder for planners to act). There's no silver bullet being offered here, but maybe they're warning us to watch out for 'friendly fire' (unintended negative impacts of promoting connectivity w/o thinking about disease).<br /><br /><br /><strong>ORGANIZATIONAL BEHAVIOR CHANGE:</strong><br />Ferraro et al. 2019 is a non-peer-reviewed working paper that asks whether behavioral psychology nudges known to influence individuals work on organizations too. They looked at a national organization asking for voluntary membership does from 3,000 nonprofits, and tested 1) crafting a clear and salient ask to emphasize public benefits, 2) publicly sharing who contributed and by how much, and 3) showing quarterly progress towards a national goal. All had no effect (each treatment on average made contributions very slightly lower, but w/o statistical significance). The authors hypothesize (w/ evidence from other studies) that group decision making makes orgs less responsive than individuals to these kinds of interventions. An interesting follow-up study would be to target individuals with the individual authority to make decisions that affect the broader organization and see if that works.<br /><br /><br /><strong>REFERENCES:</strong></p><p>Brisco, E., Kulinskaya, E., & Koricheva, J. (2023). Assessment of temporal instability in the applied ecology and conservation evidence base. Research Synthesis Methods, November, 1–15. https://doi.org/10.1002/jrsm.1691<br /><br />Ferraro, P. J., Weigel, C., An, J., & MESSER, K. D. (2019). Nudging Organizations: Evidence from three large-scale field experiments (Vol. 21211). https://doi.org/10.1257/rct.4238-3.0<br /><br />Iverson, A. R., Waetjen, D., & Shilling, F. (2024). Functional landscape connectivity for a select few: Linkages do not consistently predict wildlife movement or occupancy. Landscape and Urban Planning, 243(March 2023), 1–12. https://doi.org/10.1016/j.landurbplan.2023.104953<br /><br />Jasechko, S., Seybold, H., Perrone, D., Fan, Y., Shamsudduha, M., Taylor, R. G., Fallatah, O., & Kirchner, J. W. (2024). Rapid groundwater decline and some cases of recovery in aquifers globally. Nature, 625(7996), 715–721. https://doi.org/10.1038/s41586-023-06879-8<br /><br />Thurman, L. L., Alger, K., LeDee, O., Thompson, L. M., Hofmeister, E., Hudson, J. M., Martin, A. M., Melvin, T. A., Olson, S. H., Pruvot, M., Rohr, J. R., Szymanksi, J. A., Aleuy, O. A., & Zuckerberg, B. (2024). Disease‐smart climate adaptation for wildlife management and conservation. Frontiers in Ecology and the Environment, 1–10. https://doi.org/10.1002/fee.2716<br /><br /><br />Sincerely,<br /> <br />Jon<br /> <br />p.s. The photo is of a piece called "Shift" by Lisa Wood Studios, and it cycled between saying "Unconscious consumption" and "Conscious conservation" (presumably what we have now) and then as shown above "conscious consumption" and "unconscious conservation" (which makes less sense to me, but presumably means we're mindful of our choices and conservation happens automatically?</p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-6729122912873567872024-02-01T08:30:00.001-05:002024-02-01T08:30:00.131-05:00February 2024 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/53433474483/" title="Snowflake ornament illuminated by Christmas tree lights"><img alt="Snowflake ornament illuminated by Christmas tree lights" height="225" src="https://live.staticflickr.com/65535/53433474483_4cfca0c3dc_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script><p> Hello,</p><br />This month is a bit of a grab bag again with an article on freshwater protection, another on koala-vehicle strikes, and two on soil carbon (both offering caution on the potential and flagging complexity).<br /><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a data-cke-saved-href="http://eepurl.com/diB0nr" href="http://eepurl.com/diB0nr">http://b</a><a data-cke-saved-href="http://bit.ly/sciencejon" href="http://bit.ly/sciencejon" target="_blank">it.ly/sciencejon</a> (no need to email me).<br /><br /><strong>FRESHWATER:</strong><br />Flitcroft et al. 2023 notes that counting effective freshwater protection globally is really hard (as is getting effective protection to happen). Fig 1 has a nice summary of how restrictive different protection mechanisms are. They also call for both better management of existing protected areas (PAs) to include freshwater conservation needs, and protections for freshwater in new places. While issues around data resolution and data availability continue to pose challenges to freshwater conservation, they argue that more explicit consideration of both freshwater and terrestrial objectives in any area-based protection is a good start.<br /><br /><br /><strong>WILDLIFE-VEHICLE CONFLICTS:</strong><br />Dexter et al. 2023 makes a point that seems obvious once you think about it, but which was new to me. Namely, hotspots of wildlife-vehicle collisions (they looked at koala strikes) are likely to be very dynamic over time as wildlife populations grow and shrink, as land use change drives shifts in their movement, and as roads and traffic change. They make the point that wildlife crossings are generally cited based on past collision data, and found that collision hotspots decline over time (as nearby populations decline and/or move). There was some unspecified 'road mitigation' which could have partially driven the reductions but the authors said the mitigation wasn't sufficient to explore the decline (pointing to unpublished data, unfortunately). They recommend instead taking a broader landscape approach considering habitat and trends as opposed to focusing crossings at local collision hotspots, and including crossings or other mitigation early when making infrastructure changes.<br /><br /><br /><strong>SOIL CARBON:</strong><br />Ogle et al. 2023 looks at the soil carbon portion of U.S. plans to meet their contribution to the Paris agreement on climate mitigation. They review several well known challenges w/ soil carbon (C): changes are hard to predict and measure accurately, that additionality and permanence can be challenges, and that changing practices can have undesirable side-effects (increasing emissions from soil of strong GHGs like nitrous oxide or methane, shifting emissions to other farms, etc.). See Table 1 for a summary. They also provide an overview of policy options including mandates, subsidies and incentives, C taxes, and C offsets (see Table 2). They call for a suite of research to investigate these challenges and look for a path forward if one exists.<br /><br />Wang et al. 2023 is a helpful review of the degree to which soil carbon sequestration can offset greenhouse gas (GHG) emissions from ruminants (mostly cattle, but also sheep, goats, and buffaloes). It's a nice example of fairly simple analysis revealing important insights. Their top level finding is that to offset ruminant emissions from manure and burping over a 100 year timeframe, we would need to roughly triple the current total global carbon stock in managed grasslands (adding 200% to existing stocks), with regional increases needed from ~25%-2000% (Fig 4b, and see 4c which is per ha). That large an increase is not feasible; while reducing net emissions on ranches is important, we shouldn't expect to get the global beef & other ruminant sector to help mitigate climate change on net. That's perhaps obvious, but fringe local cases of low-density ranches w/ lots of nature potentially being carbon negative are often cited as examples of something globally scalable, so it's a useful reminder that they are not unless we reduce the global supply of ruminants (farm and eat less of their meat and dairy). Fig 3 summarizes how cattle factor into this in a different way: depending on how a given grassland can sequester and how much methane each cow produces, the "offsettable" cattle density ranges from 0 to 1.2 (for the very best case scenario).<br /><br /><br /><strong>REFERENCES:</strong><br />Dexter, C. E., Scott, J., Blacker, A. R. F., Appleby, R. G., Kerlin, D. H., & Jones, D. N. (2023). Koalas in space and time: Lessons from 20 years of vehicle‐strike trends and hot spots in South East Queensland. Austral Ecology, June 2021, 1–18. https://doi.org/10.1111/aec.13465<br /><br />Flitcroft, R. L., Abell, R., Harrison, I., Arismendi, I., & Penaluna, B. E. (2023). Making global targets local for freshwater protection. Nature Sustainability. https://doi.org/10.1038/s41893-023-01193-7<br /><br />Ogle, S. M., Conant, R. T., Fischer, B., Haya, B. K., Manning, D. T., McCarl, B. A., & Zelikova, T. J. (2023). Policy challenges to enhance soil carbon sinks: the dirty part of making contributions to the Paris agreement by the United States. Carbon Management, 14(1). https://doi.org/10.1080/17583004.2023.2268071<br /><br />Wang, Y., de Boer, I. J. M., Persson, U. M., Ripoll-Bosch, R., Cederberg, C., Gerber, P. J., Smith, P., & van Middelaar, C. E. (2023). Risk to rely on soil carbon sequestration to offset global ruminant emissions. Nature Communications, 14(1), 7625. https://doi.org/10.1038/s41467-023-43452-3<br />Sincerely,<br /> <br />Jon<br /> <br />p.s. This is a photo of a handmade glass snowflake ornament reflecting and transmitting several colors of Christmas tree lightsJonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-28532050461990935322024-01-25T11:56:00.001-05:002024-01-25T11:56:05.527-05:00Best of 2023 science summaries<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/53394277790/in/photolist-2ppQUkS-2ppVTMo-2ppXgAP-2ppXgSV-2ppXLCg-2ppXLNG-2ppXPzt-2pq3ZJg-2pshPXE-2pshVJ4-2psi1xH-2psokPj-2pspaVF-2pspFXR-2pspKfx-2pthGdq-2pthJSo-2ptnhBg-2ptnqMK-2pto7eT-2ptob8j-2ptp2qP-2ptp8tA-2ptpy5F-2ptpKEp-2pkZstH-2pkZtCS-2pkZu9B-2pkZuGW-2pm5c4Z-2pm5epf-2pm66qV-2pm6bW9-2pm6GTj-2pm7nVZ-2pm7o8T-2pm7oSP-2pm7tQj-2pm9x2n-2pm9DAV-2pmeh7X-2pmfkNV-2pmfZtA-2pmgCyo-2ppKcH6" title="Luna resting her head on Kong (on Jon's lap)"><img alt="Luna resting her head on Kong (on Jon's lap)" height="300" src="https://live.staticflickr.com/65535/53394277790_e76473a880_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script>
<p><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">Happy new year!</span></p><p style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px; line-height: 24px; margin: 10px 0px; padding: 0px; text-size-adjust: 100%;"><br />As usual here are my favorite 15 articles from 2023, and a few other things you may have missed.<br /><br />But first - if you or someone you know are looking for a sweet and loving dog in your life (or two?), both of our foster dogs Luna (top head above) and Kong (supporting head) are still up for adoption! You can <a href="https://www.shelterluv.com/embed/animal/62357516" style="color: #007c89; text-size-adjust: 100%;" target="_blank">read about Kong</a>, <a href="https://photos.app.goo.gl/uKr1FLXy1NJzkv2Q7" style="color: #007c89; text-size-adjust: 100%;" target="_blank">see how cute he is</a>, <a href="https://www.shelterluv.com/embed/animal/79429154" style="color: #007c89; text-size-adjust: 100%;" target="_blank">read about Luna</a>, and <a href="https://photos.app.goo.gl/UiiL9wP53ALgX2mR9" style="color: #007c89; text-size-adjust: 100%;" target="_blank">see how cute <em>she </em>is</a>.</p><ol style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"><li style="text-size-adjust: 100%;">A summary of the IPCC's latest report (AR6) came out, <a href="https://mailchi.mp/65e0bf8c18ce/april-2023-science-summary?e=10dbe3f36d" style="color: #007c89; text-size-adjust: 100%;" target="_blank">click here for my brief summary of that summary</a></li><li style="text-size-adjust: 100%;"><a href="https://wapo.st/3MLWDes" style="color: #007c89; text-size-adjust: 100%;" target="_blank">The earth had its first day that was 2C warmer than the historic pre-industrial average (1850-1900)</a>. We're still a ways from an AVERAGE of 2C warmer than pre-industrial, but still a bummer.</li><li style="text-size-adjust: 100%;">Last month I shared some (not very well-informed) thoughts about how I'm using artificial intelligence (AI), specifically large language models (LLMs) like ChatGPT and Google's Bard. Scroll to the bottom of <a href="https://mailchi.mp/5d4bf60238aa/december-2023-science-summary?e=10dbe3f36d" style="color: #007c89; text-size-adjust: 100%;" target="_blank">my December summary</a> to see them</li></ol><p style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px; line-height: 24px; margin: 10px 0px; padding: 0px; text-size-adjust: 100%;">On to the science articles!<br /><br /><strong>PEOPLE AND NATURE:</strong><br /><strong>Chaplin-Kramer et al. 2022</strong> is a great <strong>global summary of 14 ecosystem services</strong> I've been waiting to see for years! Their big finding is that 90% of nature's local contributions to people within each country come from a total of 30% of global land area and 24% of coastal waters (EEZs). Globally only 15% of those places are protected. The land and water needed is uneven by country (e.g., the US needs 37% of land and 15% of coastal waters), and protection varies too. See Fig 1 for the areas that provide the most benefit per unit area. The land required would be lower if optimizing globally, but at the cost of less equitable benefit distribution. The 2 global ones (carbon storage and moisture recycling) need 44% of land (optimized globally) to stay at 90% of current levels, mostly overlapping with the 30% (see Fig 3). Roughly 87% of the world population benefits from at least one of the ecosystem services, but benefits are not distributed equally (see Fig 2). The local services include: water quality (regulating nitrogen and sediment), crop pollination, livestock fodder, production of timber and fuelwood, flood regulation, fish harvest (from rivers and oceans), recreation (on land and oceans), and coastal risk reduction. If interested you can get combined GIS data from <a href="https://osf.io/r5xz7/?view_only=d611a688525f4ceb8db4ef4e7528b0e8" style="color: #007c89; text-size-adjust: 100%;" target="_blank">https://osf.io/r5xz7/?view_only=d611a688525f4ceb8db4ef4e7528b0e8</a> or one of the authors (Rachel Neugarten) is happy to send individual maps and data.<br /><br /><strong>Cinner et al. 2019</strong> is a 16 year<strong> study of rotational fishing / closure in Papua.</strong> They found success in compliance with the system (due to strong social cohesion driven by leaders sharing info, a "carrot and stick" approach, and lots of community participation) BUT even though closed areas rebounded, over the study period fish biomass dropped by about half. So even though the closure program worked as intended, it wasn't enough to offset overfishing when areas were open.<br /><br /><strong>Grenz & Armstrong 2023</strong> is an article <strong>criticizing "pop-up restoration," </strong>a term they coin for ecological restoration that 1) lacks long-term engagement and monitoring, 2) denies people use of lands (even Indigenous people who have been there for millennia), and 3) sets fixed ecological baselines or goals even for ecosystems which historically were highly managed and dynamic. They describe two use cases where management outcomes preferred by Indigenous people were ignored, instead managing for outcomes preferred by non-Indigenous ranchers or residents. They call for restorative justice being the norm, and ethical engagement with communities in each specific place (rather than coopting and misusing Indigenous knowledge). They also call for more openness to evolving needs and conditions of both people and ecosystems, and acknowledging failures and wrongdoing.<br /><br /><br /><strong>GENDER AND CONSERVATION:</strong><br /><strong>James et al. 2023 </strong>asked over 900 <strong>science & conservation staff </strong>of The Nature Conservancy <strong>about their careers and influence, and how they perceived their gender as impacting that.</strong> We found that women had less influence, experienced many barriers to their careers (including harassment, discrimination, and fear of retaliation for speaking out), and that men overestimated gender equity. Only have 5 minutes? Skip to the recommendations on page 7 (we ask orgs to: show public leadership on equity, improve transparency and accountability, diversify teams and improve career pathways for women, be flexible, include training and mentoring as part of broader change, help women connect, address sexual discrimination and harassment, and consider intersectionality). If you have 15 minutes more, read the quotes in Table 2 (p5-8) because they're really compelling and illustrative. Or if you're with the half of men and 3/4 of women in our sample who think we have more to do on gender equity (rather than that we've already "gone overboard" or that it's not an issue as some men reported), just read the whole damn paper because there's a lot of interesting detail and nuance in the results. I learned a ton while helping out on it, and I'm excited to start advocating for the recommendations. You can read it at: https://bit.ly/TNCgenderpaper or a short blog at https://blog.nature.org/science-brief/gender-bias-holds-women-back-in-conservation-careers/ <br /><br /><br /><strong>SCIENCE COMMUNICATIONS:</strong><br /><strong>Toomey et al. 2023</strong> is a nice reminder that just <strong>sharing information doesn't usually change minds</strong>. They challenge the idea that facts & scientific literacy lead to research being applied, and that broad communications targeting as many individuals as possible are the most effective way to share those facts. Instead they recommend appealing to values and emotions, and strategically targeting audiences by considering social networks (drawing on science about behavior change) and social norms. I love the conclusion that "this article may not change your mind" but that they hope it will inspire reflection. I also like the use of the backronym WEIRD (Western, Educated, Industrialized, Rich, Democratic) to describe countries like the US.<br /><br /><br /><strong>LEARNING FROM FAILURE:</strong><br /><strong>Dickson et al. 2023 </strong>piqued my curiosity by <strong>breaking down different causes of conservation failure and how to respond</strong>. I generally dislike taxonomy papers, and find them academic and hard to apply. But understanding how to respond to different kinds of failure seems helpful, especially for the most common causes (including lacking a sufficiently robust theory of change. see table 2 for more). Their taxonomy has 59 (!) root causes, grouped into 6 categories: 1) planning, design, or knowledge (e.g., inadequate theory of change); 2) team dynamics (e.g., disagreements on what priorities should be); 3) project governance (e.g., lack of a technical advisory group); 4) resources (e.g., staff overloaded or lack needed technical expertise); 5) stakeholder relationships (e.g., lack of buy-in from gov't); and 6) unexpected external events (e.g., natural disaster, war, disease, etc.). After reading all the ways to fail, my main take away is that failure will happen sometimes and we need to focus on how to learn and pivot. The other big one is that while teams often resent spending a few hours developing and refining a theory of change (ToC), that is likely time well spent given that how often an insufficient ToC was listed as a cause of failure.<br /><br /><br /><strong>CLIMATE MITIGATION:</strong><br /><strong>Duncanson et al. 2023</strong> estimates <strong>how much global forested protected areas may be reducing climate change</strong>. They matched forested protected areas to similar forested unprotected areas using data from 2000 (land cover, ecoregion, and biome; with additional control pixels that accounted for population etc. - see Table S1). Then they used the new (2019) GEDI lidar data to estimate aboveground forest biomass in 2020. 63% of forested PAs had significantly higher biomass than matched unprotected areas; on average PAs have 28% more aboveground biomass. Over a third of that effect globally comes from Brazil; Africa had less C dense forests and more human pressures on both PAs and unprotected areas. As you'd guess, most of the difference in unprotected sites was due to deforestation. But in 18% of PAs carbon was higher than unprotected sites even though optical sensors didn't detect deforestation (implying LiDAR is detecting either avoided degradation and/or enhanced growth in PAs). As a final note, other research has shown that both ICESat-2 and GEDI LiDAR satellites tend to underestimate forest canopy heights (mostly irrelevant here given the matching approach, but good to know for other global estimates).<br /><br /><strong>Knauer et al. 2023</strong> has good news - better modeling estimates <strong>forests could sequester more carbon than we thought</strong>. But it's likely very small good news. Their best case is 20% more "gross primary productivity" (GPP, energy captured by photosynthesis), BUT a) that's using an extremely unlikely 'worst case' cliamte scenario which is actually hard to achieve, (RCP8.5) and b) only a fraction of GPP ends up sequestered as carbon (see Cabon et al. 2022 for more). Since forests offset roughly 25% of annual human emissions, the results likely mean <1% of annual emissions could be offset. I'll take it, but we still need to reduce gross emissions as fast as possible.<br /><br /><br /><strong>CLIMATE RESILIENCE:<br />Rubenstein et al. 2023</strong> is a systematic review of <strong>how documented range shifts</strong> (when plants and animals change where they live, presumably in response to climate change) <strong>compare to predictions</strong>. Across 311 papers, only 47% of shifts due to temperature were in expected directions (higher latitudes & elevations, and marine movement to deeper depths was seen but was non-significant). See Fig 4 for how results varied by taxonomic group, ecoystem type, and type of shift. Not many studies looked at precip but of those that did only 14% found species moving to stay in a precip niche. Note: this means simple assumptions of how species will move are of limited value, but NOT that local or regional predictions are inherently flawed. The authors note that considering local predictions of changing temp and precip will often depart from these simple assumptions, and other factors like water availability, fire, etc. are likely to be relevant. A final note on the last page was helpful: not all range shifts have equal relevance to management. In some cases a few individuals are moving to new places but most of the wildlife population doesn't shift at all. Both shifts AND non-shifts have implications for how management should change to keep species and ecosystems healthy! This paper has a LOT of nuance and variation in this paper, and a very detailed methods section with good recommendations for how scientists should continue these investigations<br /><br /><br /><strong>FRESHWATER:</strong><br /><strong>Dethier et al 2023</strong> (briefly summarized in Walmsley 2023) finds that <strong>mining in tropical countries is dramatically increasing sediment in rivers</strong>. 80% of the 173 rivers affected by mining that they studied had sediment concentrations more than double what they were prior to mining. This is a pretty coarse estimate using satellite data, so the actual sediment estimates are very rough, but the general pattern should be valid.<br /><br /><br /><strong>BIODIVERSITY:</strong><br /><strong>NatureServe's 2023 </strong>Biodiversity in Focus US report is a<strong> high level look at threatened species </strong>(imperiled or vulnerable)<strong> in the US.</strong> It's short and worth reading the whole thing. They find 34% of plant species and 40% of animal species are threatened, and 41% of the ~400 ecosystem groups in the US are at risk of "range-wide collapse" (meaning being replaced or substantially transformed). Figure 1 and 2 have breakdowns of averages for plants and animals by subgroups. For plants cacti are the worst off at 48% threatened and sedges are the least threatened at 14%. Freshwater snails are the most threatened animals (75%, and other FW groups are all more threatened than average) while birds are the least threatened (12%) and bees are about average (37%). Note that % of species that are threatened is different than looking at % of individual organisms or biomass that is threatened (all are useful metrics, Audubon's State of the Birds report looks at trends in bird population size). Figure 3 shows the most and least threatened ecosystems; unsurprisingly virtually all tropical ecosystems are threatened (they had relatively small extents originally, and are valuable for agriculture), while cliffs / rock and alpine and tundra ecosystems fare the best due to less threat of conversion to other land uses and higher rates of protection (Figure 5). They don't provide details but I would guess these are relatively short-term predictions, as climate change will threaten a lot of alpine and tundra ecosystems in the long term. Figure 4 shows how protected different species groups and ecosystems are. Almost 30% of vascular plant species are protected >50% of their range, but only 15% of vertebrate species are that protected. Finally, Figure 9b shows which states have the highest % of their area in at-risk ecosyetsms (NE, MT, and SD score the highest due to large at-risk grasslands), and Figure 11 shows priority areas for conserving imperiled species. With some exceptions (like FL) Figures 9 and 11 highlight different priority areas; Fig 11 focuses on relatively small and irreplaceable places that the most threatened species rely on, while Fig 9 focuses on more intact and lower diversity ecosystems that are at risk of being transformed (but with less potential for species extinctions). The authors conclude that the Restoring America's Wildlife Act (RAWA) guided by State Wildlife Action Plans (SWAPs) is our best bet to catalyze massive investment in conservation of the places that need it most.<br /><br /><br /><strong>WILDLIFE MANAGEMENT:</strong><br /><strong>Jewell et al. 2023</strong> surveyed directors and board members in charge of <strong>state wildlife agencies i</strong>n the SE U.S. <strong>about future conservation challenges and how they plan to respond.</strong> They found that the respondents were focused on funding and 'agency relevance' (including changing values and fewer hunters) but less concerned about climate change (see Table 2). One quote stuck out at me, which was that they saw climate change impacts as important at time-scales beyond decades, and thus not urgent to act on (they also saw it as too political). By comparison, they saw education and outreach as critical to recruit hunters and tell the public the value of hunting and fishing. Agency directors average 5 years in office, so short-term things they can do may be more appealing. The authors call for engaging decision makers around the science of how climate change is already affecting wildlife, how that is expected to shift over time, and what actions or preparations can be taken now to help.<br /><br />I couldn't resist reading <strong>Clark et al. 2023 </strong>right away despite my sad backlog. I once had a native plant garden guy tell me "at best non-native plants offer no value to pollinators and other wildlife, and most are harmful." Obviously false as an absolute! But how do they compare? Clark looked at 10 species in a Connecticut forest and found <strong>some invasive species </strong>(like honeysuckle) <strong>had more bugs </strong>(mass and protein) <strong>than the average for natives, but others </strong>(Japanese barberry) <strong>had fewer bugs</strong>. But birds seemed to forage both equally. It's a tiny study and I wish they hadn't pooled all native species, but I do like a study that counters "it depends!" to a truism in conservation.<br /><br /><br /><strong>FORESTS & FIRE:<br />Prichard et al. 2021</strong> is a review of several <strong>questions related to fire in US western forests </strong>(see Table 1 for the summary of questions & answers). They include whether and when/ how to use cutting trees and prescribed burns as tools for reducing wildfire risk and/or climate mitigation and/or ecological restoration. The authors argue that many dry forests (and some moist forests mixed into dry forest landscapes) historically experienced more frequent fires of low to moderate intensity (often set by Native Americans), but that these forests are now denser and more likely to have severe crown fires (especially as summers become warmer and drier). That in turn will cause some forests to be lost and shift to grasslands or other ecosystems. Read Table 1 for key takeaways, including that for many (not all) Western forests, thinning and prescribed burning are important tools. Side note: given the active debate on this topic, I asked for input from a few forest scientists deep in the lit, and they recommended this article.<br /><br /><br /><strong>METASCIENCE:<br />Breznau et al. 2022</strong> has some scary news about <strong>science</strong> - not only<strong> is </strong>it <strong>less reproducible than we think,</strong> we can't even figure out why results vary so much. To be fair, they note that natural sciences and/or experimental research should have less variation than social science based on existing surveys (what this study looked at). But it's still concerning! Or preliminarily concerning but waiting for many more replicas, to take their message to heart. The models the 73 teams built were: 17% positive (more immigration increases support for social policies), 25% negative (more immigration reduces support for social policies), and 58% did not find a clear effect (the confidence interval included zero, although they may have had a positive or negative average effect). 61% of researchers concluded that immigration does not reduce support for social policies, 26% concluded it DOES reduce support (the text says 28.5% but it's a typo, reinforcing the core message of the paper), and 13% concluded it couldn't be tested w/ the given data. And Fig 2 shows that not only are results and conclusions all over the place, the variation isn't explained by the variables they tracked like expertise or prior beliefs. That means researcher bias is only part of the problem. I have some questions about the metanalysis itself that make me suspect they could have explained more of the variance with different methods (ironically, that is consistent with their core findings about how small method changes can drive results). But the paper reveals two problems: 1) scientists can produce different quantitative results from the same data and hypotheses, and 2) scientists' conclusions are often not well tied to their results (this paper found only ~1/3 of variation in conclusions came from how consistent the set of models each team used were). I see a lot of #2 when I peer review papers. Let's all remain humble and skeptical, and look for more replication in 2023!<br /><br /><br /><strong>REFERENCES:</strong><br />Breznau, N., Rinke, E. M., Wuttke, A., Nguyen, H. H. V, Adem, M., Adriaans, J., Alvarez-Benjumea, A., Andersen, H. K., Auer, D., Azevedo, F., Bahnsen, O., Balzer, D., Bauer, G., Bauer, P. C., Baumann, M., Baute, S., Benoit, V., Bernauer, J., Berning, C., … Żółtak, T. (2022). Observing many researchers using the same data and hypothesis reveals a hidden universe of uncertainty. Proceedings of the National Academy of Sciences, 119(44), 1–8. https://doi.org/10.1073/pnas.2203150119<br /><br />Chaplin-Kramer, R., Neugarten, R. A., Sharp, R. P., Collins, P. M., Polasky, S., Hole, D., Schuster, R., Strimas-Mackey, M., Mulligan, M., Brandon, C., Diaz, S., Fluet-Chouinard, E., Gorenflo, L. J., Johnson, J. A., Kennedy, C. M., Keys, P. W., Longley-Wood, K., McIntyre, P. B., Noon, M., … Watson, R. A. (2022). Mapping the planet’s critical natural assets. Nature Ecology & Evolution, 7(1), 51–61. https://doi.org/10.1038/s41559-022-01934-5<br /><br />Cinner, J. E., Lau, J. D., Bauman, A. G., Feary, D. A., Januchowski-Hartley, F. A., Rojas, C. A., Barnes, M. L., Bergseth, B. J., Shum, E., Lahari, R., Ben, J., & Graham, N. A. J. (2019). Sixteen years of social and ecological dynamics reveal challenges and opportunities for adaptive management in sustaining the commons. Proceedings of the National Academy of Sciences, 116(52), 26474–26483. https://doi.org/10.1073/pnas.1914812116<br /><br />Clark, R. E. (2023). Are native plants always better for wildlife than invasives? Insights from a community-level bird- exclusion experiment. Preprint available at https://www.researchsquare.com/article/rs-3214373/v1<br /><br />Dethier, E. N., Silman, M., Leiva, J. D., Alqahtani, S., Fernandez, L. E., Pauca, P., Çamalan, S., Tomhave, P., Magilligan, F. J., Renshaw, C. E., & Lutz, D. A. (2023). A global rise in alluvial mining increases sediment load in tropical rivers. Nature, 620(7975), 787–793. https://doi.org/10.1038/s41586-023-06309-9<br /><br />Dickson, I., Butchart, S. H. M., Catalano, A., Gibbons, D., Jones, J. P. G., Lee‐Brooks, K., Oldfield, T., Noble, D., Paterson, S., Roy, S., Semelin, J., Tinsley‐Marshall, P., Trevelyan, R., Wauchope, H., Wicander, S., & Sutherland, W. J. (2023). Introducing a common taxonomy to support learning from failure in conservation. Conservation Biology, 37(1), 1–15. https://doi.org/10.1111/cobi.13967<br /><br />Duncanson, L., Liang, M., Leitold, V., Armston, J., Krishna Moorthy, S. M., Dubayah, R., Costedoat, S., Enquist, B. J., Fatoyinbo, L., Goetz, S. J., Gonzalez-Roglich, M., Merow, C., Roehrdanz, P. R., Tabor, K., & Zvoleff, A. (2023). The effectiveness of global protected areas for climate change mitigation. Nature Communications, 14(1), 2908. https://doi.org/10.1038/s41467-023-38073-9<br /><br />Grenz, J., & Armstrong, C. G. (2023). Pop-up restoration in colonial contexts: applying an indigenous food systems lens to ecological restoration. Frontiers in Sustainable Food Systems, 7(September), 1–12. https://doi.org/10.3389/fsufs.2023.1244790<br /><br />James, R., Fisher, J. R. B., Carlos-Grotjahn, C., Boylan, M. S., Dembereldash, B., Demissie, M. Z., Diaz De Villegas, C., Gibbs, B., Konia, R., Lyons, K., Possingham, H., Robinson, C. J., Tang, T., & Butt, N. (2023). Gender bias and inequity holds women back in their conservation careers. Frontiers in Environmental Science, 10(January), 1–16. https://doi.org/10.3389/fenvs.2022.1056751 or https://bit.ly/TNCgenderpaper<br /><br />Jewell, K., Peterson, M. N., Martin, M., Stevenson, K. T., Terando, A., & Teseneer, R. (2023). Conservation decision makers worry about relevancy and funding but not climate change. Wildlife Society Bulletin, November 2022, 1–14. https://doi.org/10.1002/wsb.1424<br /><br />Knauer, J., Cuntz, M., Smith, B., Canadell, J. G., Medlyn, B. E., Bennett, A. C., Caldararu, S., & Haverd, V. (2023). Higher global gross primary productivity under future climate with more advanced representations of photosynthesis. Science Advances, 9(46), 24–28. https://doi.org/10.1126/sciadv.adh9444<br /><br />NatureServe. (2023). Biodiversity in Focus: United States Edition. https://www.natureserve.org/sites/default/files/NatureServe_BiodiversityInFocusReport_medium.pdf<br /><br />Prichard, S. J., Hessburg, P. F., Hagmann, R. K., Povak, N. A., Dobrowski, S. Z., Hurteau, M. D., Kane, V. R., Keane, R. E., Kobziar, L. N., Kolden, C. A., North, M., Parks, S. A., Safford, H. D., Stevens, J. T., Yocom, L. L., Churchill, D. J., Gray, R. W., Huffman, D. W., Lake, F. K., & Khatri‐Chhetri, P. (2021). Adapting western North American forests to climate change and wildfires: 10 common questions. Ecological Applications, 31(8). https://doi.org/10.1002/eap.2433<br /><br />Rubenstein, M. A., Weiskopf, S. R., Bertrand, R., Carter, S. L., Comte, L., Eaton, M. J., Johnson, C. G., Lenoir, J., Lynch, A. J., Miller, B. W., Morelli, T. L., Rodriguez, M. A., Terando, A., & Thompson, L. M. (2023). Climate change and the global redistribution of biodiversity: substantial variation in empirical support for expected range shifts. Environmental Evidence, 12(1), 7. https://doi.org/10.1186/s13750-023-00296-0<br /><br />Toomey, A. H. (2023). Why facts don’t change minds: Insights from cognitive science for the improved communication of conservation research. Biological Conservation, 278(December 2022), 109886. https://doi.org/10.1016/j.biocon.2022.109886<br /><br />Walmsley, B. (2023). Satellite images show the widespread impact of mining on tropical rivers. Nature, 620(7975), 729–730. https://doi.org/10.1038/d41586-023-02349-3<br /><br />Sincerely,<br /> <br />Jon<br /></p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-39792861177706945752024-01-25T11:54:00.000-05:002024-01-25T11:54:00.321-05:00December 2023 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/53299743756/in/photolist-2pcV7Tf-2pgqpN2" title="Anglerfish pumpkin / jack-o'-lantern"><img alt="Anglerfish pumpkin / jack-o'-lantern" height="225" src="https://live.staticflickr.com/65535/53299743756_b949a9162e_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script>
<p> <span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">Hi,</span></p><p style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px; line-height: 24px; margin: 10px 0px; padding: 0px; text-size-adjust: 100%;"><br />On Friday Nov 17, the earth was 2C warmer than historic pre-industrial average (1850-1900), and 1.17C over the 1991-2020 average. This does not mean the earth has warmed 2C yet! That would require a sustained set of temperatures high above average. But still not great news. https://wapo.st/3MLWDes<br /><br />This month I have three science articles but am also sharing some informal thoughts about how scientists might want to consider using (and not using) generative artificial intelligence tools.<br /><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a href="http://eepurl.com/diB0nr" style="color: #007c89; text-size-adjust: 100%;">http://b</a><a href="http://bit.ly/sciencejon" style="color: #007c89; text-size-adjust: 100%;" target="_blank">it.ly/sciencejon</a> (no need to email me).<br /><br /><strong>CLIMATE CHANGE:</strong><br />Knauer et al. 2023 has good news - better modeling estimates forests could sequester more carbon than we thought. But it's likely very small good news. Their best case is 20% more "gross primary productivity" (GPP, energy captured by photosynthesis), BUT a) that's using an extremely unlikely 'worst case' cliamte scenario which is actually hard to achieve, (RCP8.5) and b) only a fraction of GPP ends up sequestered as carbon (see <a href="https://www.science.org/doi/10.1126/science.abm4875" style="color: #007c89; text-size-adjust: 100%;" target="_blank">Cabon et al. 2022</a> for more). Since forests offset roughly 25% of annual human emissions, the results likely mean <1% of annual emissions could be offset. I'll take it, but we still need to reduce gross emissions as fast as possible.<br /><br /><strong>CATTLE RANCHING</strong>:<br />Chiaravalloti et al. 2023 assessed how well cattle ranches in the Brazilian Pantanal (among the world's largest wetlands) aligned w/ Elinor Ostrom's principles (for sustainable use of natural resources, see Table 2 for a nice summary). They interviewed 49 cattle ranchers, other people working in the beef supply chain, conservationists, and policy makers. Flooding, very low stocking density, lack of transportation, and the fire regime all make ranching in the Pantanal unusual. They found the Pantanal ranches do well on the first 3 principles: clearly defined boundaries, appropriate rules for resource use reflecting local conditions, and collective decision making. But there is a lack of the other principles: limited monitoring, no graduated sanctions, lack of accessible conflict resolution, lack of recognition for self-governance on sustainability, and nested enterprises that coordinate governance and monitoring and the rest. They call for a series of specific recommendations to address these deficits, including celebrating early examples of things that are working well.<br /><br />Gomes et al. 2023 is a case study in the Brazilian Pantanal assessing 14 cattle ranches (cow-calf operations) using the Fazenda Pantaneira Sustentável (FPS) tool. The tool assesses 1) financial performance (costs of management, inputs, labor, etc., along w/ gross income), 2) productive performance (which favors native grass forage availability and producing calves), and 3) environmental performance (landscape diversity conservation index, which favors diverse vegetation types that have been maintained on the ranch), and combined them into a composite score. Table 2 has the results and highlights how much variation there is across ranches. Table 3 has an easier to read narrative summary of how the ranches are performing. They recommend using the relative high performing ranches as baselines for what performance level the others should aspire to.<br /><br /><strong>THOUGHTS ON GENERATIVE ARTIFICIAL INTELLIGENCE (AI)</strong>:<br /><u>I am in no way an expert on AI.</u> I am a person who has played with a variety of tools, and is sometimes asked for my opinion. <u>The thoughts here are my own, and don't reflect the views of my employer or anyone who actually knows what they're taking about</u>. They are general guidance skewed by what I've tried, and the tools evolve fast so could already be wrong. Two things to keep in mind throughout - 1) when you ask AI for answers they often confidently provide wrong answers, and 2) don't put sensitive / non-public information in there as some of these tools have the right to reuse or share what you put in. Watch out for those!<br /><br />With that caveat, I wanted to share some suggestions for how to use generative AI (including large language models [LLMs] like ChatGPT and Bard, plus image generating tools like DALL-E). Other kinds of AI are not included. I split use cases into three categories:<br /><br /><u><em>GREEN: relatively safe uses/ DO</em></u>:</p><ul style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"><li style="text-size-adjust: 100%;"><strong>Reword</strong> emails / blogs / reports, including for length or tone or clarity. LLMs perform very well at producing text which is clear and understandable to a general audience, with few to no grammatical errors. It's also surprisingly good at adjusting emotional tone, e.g.,<a href="https://www.nytimes.com/2023/06/12/health/doctors-chatgpt-artificial-intelligence.html?unlocked_article_code=1.AU0.bSZD.sSOEp32mUojS&smid=url-share" style="color: #007c89; text-size-adjust: 100%;" target="_blank"> doctors are using ChatGPT to write more empathetic emails to patients</a>. Again, be wary of putting in sensitive info. A final edit and review for factual accuracy is essential. </li><li style="text-size-adjust: 100%;">Use Elicit.com for <strong>screening a set of science paper</strong> PDFs (it produces a spreadsheet with summaries, methods, etc. which a researcher can use to decide where to start reading). Use “detailed summary” as the <a href="https://mailchi.mp/3856bed1637d/march-2023-science-summary-with-more-ai-summaries?e=10dbe3f36d" style="color: #007c89; text-size-adjust: 100%;" target="_blank">shorter summary leaves important stuff out (the link does to a detailed review I wrote of Elicit)</a>. This used to be free but they charge you now.</li><li style="text-size-adjust: 100%;">Help finding other kinds of information hard to find with traditional <strong>search</strong> engines. For example, a search for strategic planning frameworks for nonprofits (roughly similar to the conservation standards) was mostly unproductive, but similar queries to Bard produced an excellent science paper with a comparison between 5 frameworks.<ul><li style="text-size-adjust: 100%;">Note that this only means looking for sources you will actually read, NOT asking it to pull out facts. It's a great way to find references you may otherwise miss.</li></ul></li><li style="text-size-adjust: 100%;">Help finding hotels that meet criteria you can’t easily filter on in other travel sites (like quiet, dining options, offering special rates, etc.). Again - read reviews and the hotel website to verify the info, in some cases I was offered hotels that did not meet my criteria, but in other cases it helped me.</li></ul><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"> </span><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><u style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"><em>YELLOW: offers value but also some risk/ CAUTIOUSLY DO:</em></u><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"></span><ul style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"><li style="text-size-adjust: 100%;">Look for key facts buried in long reports / science papers (either w/ ChatPDF or online LLMs) - then verify those facts are real / correct / actually in the source (ChatPDF will often tell you the correct page number for a factual assertion if asked). It is typically faster than reading long documents or searching through them (e.g., I used for the suites of IPCC AR6 reports). The 'cautiously' part is that I can't stress enough that these tools often <em>make things up and provide fictional sources!</em></li><li style="text-size-adjust: 100%;">Summarize science papers or other long reports in plain language. Again, check any key points for veracity. Here's a long review <a href="https://mailchi.mp/84b96131440f/february-2023-science-summary-including-chatgpt-summaries?e=10dbe3f36d" style="color: #007c89; text-size-adjust: 100%;" target="_blank">comparing how ChatGPT summaries of papers compare to my own</a>, and another one <a href="https://mailchi.mp/3856bed1637d/march-2023-science-summary-with-more-ai-summaries?e=10dbe3f36d" style="color: #007c89; text-size-adjust: 100%;" target="_blank">evaluating Elicit's short and detailed summaries of papers I co-authored</a>.</li><li style="text-size-adjust: 100%;">Write sample code you either don't know how to write or that would take a long time. It may perform poorly and/or be hard to debug, but may be ‘good enough’ in cases where time is limited. On the other hand, in some cases it could introduce security and/or performance risks. This is best when you know how to code (and understand code you read) and are looking for sample code to start with.</li><li style="text-size-adjust: 100%;">Use Elicit.com to identify potential issues / problems with science papers. While existing functions around critiques of papers and methodological limitations or conflicts of interest do not work very well, in some cases they do work and have potential if refined. I'll say it again: verify anything it tells you.</li><li style="text-size-adjust: 100%;">List common arguments for or against a given topic. This can provide helpful context but should not be treated as definitive</li><li style="text-size-adjust: 100%;">Produce an initial outline for something like a paper or a report – suggesting possible topics and how to organize them as a way to stimulate thought and get started. My teacher friends also said it can be great for suggesting things to include in a syllabus.</li></ul><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"> </span><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><u style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"><em>RED: use cases to be avoided/ DO NOT:</em></u><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"></span><ul style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"><li style="text-size-adjust: 100%;">Ask for facts and trust the results w/o carefully checking references (LLMs regularly fabricate false info and <a href="https://www.marketplace.org/shows/marketplace-tech/dont-be-surprised-by-ai-chatbots-creating-fake-citations/" style="color: #007c89; text-size-adjust: 100%;" target="_blank">provide fictional references [hallucitations]</a> for it)</li><li style="text-size-adjust: 100%;">Assume content provided (code, images, text) can be used w/o copyright issues. Often it cannot, and using a bit of LLM-generated content can screw w the copyright of the bigger report it goes into.</li><li style="text-size-adjust: 100%;">Assume LLMs will include caveats or methodological limitations when reporting results from reports (they generally do not)</li><li style="text-size-adjust: 100%;">Put sensitive, nonpublic, or other confidential text, data, or code into LLMs</li><li style="text-size-adjust: 100%;">Assume you know how the tools work. They change so fast you probably don't. Treat it as a black box which sometimes spits out candy, but sometimes you get those Harry Potter jelly beans that taste like vomit or earwax.</li></ul><p style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px; line-height: 24px; margin: 10px 0px; padding: 0px; text-size-adjust: 100%;"><br />Again, please use the above as ideas you can try out and verify for yourself. Don't trust my judgment on AIs any more than you would trust their assessment of their limitations.<br /><br /><br /><strong>REFERENCES:</strong></p><p style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px; line-height: 24px; margin: 10px 0px; padding: 0px; text-size-adjust: 100%;">Cabon, A., Kannenberg, S. A., Arain, A., Babst, F., Baldocchi, D., Belmecheri, S., Delpierre, N., Guerrieri, R., Maxwell, J. T., McKenzie, S., Meinzer, F. C., Moore, D. J. P., Pappas, C., Rocha, A. V., Szejner, P., Ueyama, M., Ulrich, D., Vincke, C., Voelker, S. L., … Anderegg, W. R. L. (2022). Cross-biome synthesis of source versus sink limits to tree growth. Science, 376(6594), 758–761. https://doi.org/10.1126/science.abm4875<br /><br />Chiaravalloti, R. M., Tomas, W. M., Akre, T., Morato, R. G., Camilo, A. R., Giordano, A. J., & Leimgruber, P. (2023). Achieving conservation through cattle ranching: The case of the Brazilian Pantanal. Conservation Science and Practice, September. https://doi.org/10.1111/csp2.13006<br /><br />Gomes, E. G., Santos, S. A., Paula, E. S. de, Nogueira, M. A., Oliveira, M. D. de, Salis, S. M., Soriano, B. M. A., & Tomas, W. M. (2023). Multidimensional performance assessment of a sample of beef cattle ranches in the Pantanal from a data envelopment analysis perspective. Ciência Rural, 53(12), 1–12. https://doi.org/10.1590/0103-8478cr20220595<br /><br />Knauer, J., Cuntz, M., Smith, B., Canadell, J. G., Medlyn, B. E., Bennett, A. C., Caldararu, S., & Haverd, V. (2023). Higher global gross primary productivity under future climate with more advanced representations of photosynthesis. Science Advances, 9(46), 24–28. https://doi.org/10.1126/sciadv.adh9444<br /><br />Sincerely,<br /> <br />Jon<br /> <br />p.s. This anglerfish jack-o-lantern was carved by my wife and me; we got the pumpkin with a really long stem and wanted a theme that would make good use of it</p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-702020950670237272024-01-25T11:51:00.006-05:002024-01-25T11:51:47.993-05:00September 2023 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/53050446243/in/photolist-2oPTpqg-9UodoB-4wsDss-5xnmj3-2jCrTyF-8VDGft-8VDGvT-8VDGPD-8VDH7M-2oPQTH2-9Uod46-9Uodaa-9Uodh6-9Ur1QL-9Ur1XU" title="Seal at Starlux mini golf"><img alt="Seal at Starlux mini golf" height="300" src="https://live.staticflickr.com/65535/53050446243_3318209c08_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script>
<p> <span face="Helvetica, sans-serif" style="color: #202020; font-size: 12pt;">Hello,</span></p><p class="MsoNormal" style="line-height: 150%; margin-bottom: 7.5pt; margin-left: 0in; margin-right: 0in; margin-top: 7.5pt; margin: 7.5pt 0in;"><span face=""Helvetica",sans-serif" style="color: #202020; font-size: 12pt; line-height: 150%;">
<br />
I had high hopes to do more reading this month but international travel and
getting sick got in the way. So here are just two articles for some light
summer reading.<br />
<br />
If you know someone who wants to sign up to receive these summaries, they can
do so at <a href="https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fblogspot.us17.list-manage.com%2Ftrack%2Fclick%3Fu%3Df6d3b4e334ae8760abe359341%26id%3Db36b14f181%26e%3D10dbe3f36d&data=05%7C01%7Cjfisher%40pewtrusts.org%7Cae2a666015b041ed00c408dbaae7183b%7C95cf77fc02904b23b257df0a6fd7595d%7C0%7C0%7C638291681766562786%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=nwGgtu2v4nsLY6xdIJoSHodlZFD0wxY9ZFkop3f3Ws4%3D&reserved=0" style="-ms-text-size-adjust: 100%; -webkit-text-size-adjust: 100%; text-size-adjust: 100%;"><span style="color: #007c89;">http://b</span></a><a href="https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fblogspot.us17.list-manage.com%2Ftrack%2Fclick%3Fu%3Df6d3b4e334ae8760abe359341%26id%3Df46aafd658%26e%3D10dbe3f36d&data=05%7C01%7Cjfisher%40pewtrusts.org%7Cae2a666015b041ed00c408dbaae7183b%7C95cf77fc02904b23b257df0a6fd7595d%7C0%7C0%7C638291681766562786%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=EE4YazsAWGtsmrxe8Iux3W%2Fi3lOKakw60KYa1g%2BF%2BlU%3D&reserved=0" style="-ms-text-size-adjust: 100%; -webkit-text-size-adjust: 100%; text-size-adjust: 100%;" target="_blank"><span style="color: #007c89;">it.ly/sciencejon</span></a> (no need to email me).<br />
<br />
<strong>RANGELANDS AND SOIL C:</strong><br />
Provencher et al. 2023 models the potential carbon gains (and costs) to restore
degraded rangelands (remotely sensed) in UT and NV (and some of OR, ID, and
CA). The restoration sometimes involves herbicide to kill invasives and always
involves: seeding w/ native perennial plants, excluding grazing for only 3
years from pixels that were seeded (grazing resumes after 3 years), and ending
fire suppression. They found that invasive annual species like cheatgrass are
more common than other analyses have found (Fig 8). See Table 3 for the key
results: sequestration rates were very low in two sites (compared to less arid
ecosystems) and modest in a third. Overall they ranged from 0.022 - 0.730 t
CO2e / ha / yr (0.6-20 g C / m2 / yr). The best case scenario is in UT where
~$66 / ha delivers ~0.73 t CO2e/yr (+-50%), or ~$90 / t CO2e / yr (comparable
to reforestation). Conversely the other ranches would be >$3,000 / t CO2e /
yr. But selecting sites likely to be favorable to carbon accumulation could
help make the case for ecological restoration (with empirical data needed if
one wanted to sell carbon credits). And there is a LOT of degraded rangeland
globally, so there's room to scale. To make carbon trading feasible in the
Intermountain West, making this kind of seeding cheaper and more successful is
important. <br />
<br />
<strong>INVASIVE SPECIES:</strong><br />
I couldn't resist reading Clark et al. 2023 right away despite my sad backlog.
I once had a native plant garden guy tell me "at best non-native plants
offer no value to pollinators and other wildlife, and most are harmful."
Obviously false as an absolute! But how do they compare? Clark looked at 10
species in a Connecticut forest and found some invasive species (like
honeysuckle) had more bugs (mass and protein) than the average for natives, but
others (Japanese barberry) had fewer bugs. But birds seemed to forage both
equally. It's a tiny study and I wish they hadn't pooled all native species,
but I do like a study that counters "it depends!" to a truism in
conservation.<br />
<br />
<strong>REFERENCES:</strong><o:p></o:p></span></p>
<span face=""Helvetica",sans-serif" style="color: #202020; font-size: 12pt; mso-ansi-language: EN-US; mso-bidi-font-family: Calibri; mso-bidi-language: AR-SA; mso-fareast-font-family: Calibri; mso-fareast-language: EN-US; mso-fareast-theme-font: minor-latin;">Clark, R. E. (2023). Are native plants always better for wildlife than
invasives ? Insights from a community-level bird- exclusion experiment.<br />
<br />
Provencher, L., Byer, S., Frid, L., Senthivasan, S., Badik, K. J., & Szabo,
K. (2023). Carbon Sequestration in Degraded Intermountain West Rangelands,
United States. Rangeland Ecology & Management, 90, 22–34. <a href="https://doi.org/10.1016/j.rama.2023.05.004">https://doi.org/10.1016/j.rama.2023.05.004</a><br />
<br />
<br />
Sincerely,<br />
<br />
Jon<br />
<br />
p.s. This is a photo of a fountain at a mini golf course in Wildwood, NJ</span>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-28947275670685533712023-11-01T08:33:00.009-04:002024-01-25T11:51:59.946-05:00November 2023 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/53278439681/in/datetaken/" title="Jon and Kong napping on the couch"><img alt="Jon and Kong napping on the couch" height="300" src="https://live.staticflickr.com/65535/53278439681_3886505c4b_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script>
<p>Hello again,</p><p><br />This month I review papers on inequitable restoration, the carbon impact of working from home, learning from failure, and connectivity. I also have some notes on using AI to help with your lit review. And a shameless plug for our foster dog (Kong) pictured above.<br /><br />Kong is a an exuberant dog ready to bring some joy to someone’s life! He is a great partner for the dog park, hiking, playing ball in the yard, and lots and lots of cuddling. He has so much love to give, and likes every person and dog he meets. He would enjoy a playful dog brother or sister, and gets along well with cats and kids. If you live in the DC area and are <a data-cke-saved-href="https://www.homewardtrails.org/adopt-a-pet/dogs-for-adoption/#sl_embed&page=shelterluv_wrap_1601325889832%2Fembed%2Fanimal%2F62357516" href="https://www.homewardtrails.org/adopt-a-pet/dogs-for-adoption/#sl_embed&page=shelterluv_wrap_1601325889832%2Fembed%2Fanimal%2F62357516" target="_blank">potentially interested in adopting Kong, here's more info about him</a>. And here are <a data-cke-saved-href="https://photos.google.com/share/AF1QipOPrRt57tqzgV_j3Bz1Gz-y7h0FmMIc-k_mY0ijkKAKaW_X_EdSzfOnIxL_lshZBw?key=S24ydmVsSTc3RXYwdXhBOUpxeUNmVzFVdDU5Q1pR" href="https://photos.google.com/share/AF1QipOPrRt57tqzgV_j3Bz1Gz-y7h0FmMIc-k_mY0ijkKAKaW_X_EdSzfOnIxL_lshZBw?key=S24ydmVsSTc3RXYwdXhBOUpxeUNmVzFVdDU5Q1pR" target="_blank">more cute photos and videos of Kong</a> which everyone can probably benefit from.<br /><br />A colleague recently asked me for advice on using AI to help make it easier to run a journal club. She wanted help narrowing down which papers to read and recommend to the group. My favorite tool for this purpose is still elicit (elicit.org, which I reviewed in my <a data-cke-saved-href="https://mailchi.mp/3856bed1637d/march-2023-science-summary-with-more-ai-summaries?e=10dbe3f36d" href="https://mailchi.mp/3856bed1637d/march-2023-science-summary-with-more-ai-summaries?e=10dbe3f36d" target="_blank">March 2023 summary</a>). Just upload a folder of manuscript PDFs, be sure to turn on the "detailed summary" field (the default summary leaves out enough to be misleading), and review the spreadsheet of summaries you get. It's a great way to pick which articles to start with and which to condemn to the "maybe eventually I'll read this but who am I kidding" folder unless something changes. <br /><br />Also, ChatGPT sometimes refuses to summarize science papers now (saying it can't review external sites), but I did put in some Bard summaries below to compare to the ones I wrote (I only pulled them after I was done writing mine). Bard rolled out a feature in September where you can sometimes check its sources (since it still is prone to getting facts wrong), but in recent testing there was no text available for me to easily check with their tool.<br /><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a data-cke-saved-href="http://eepurl.com/diB0nr" href="http://eepurl.com/diB0nr">http://b</a><a data-cke-saved-href="http://bit.ly/sciencejon" href="http://bit.ly/sciencejon" target="_blank">it.ly/sciencejon</a> (no need to email me).</p><p><br /><br /><strong>INDIGENOUS KNOWLEDGE</strong><br /><u><em>Jon summary:</em></u><br />Grenz & Armstrong 2023 is an article criticizing "pop-up restoration," a term they coin for ecological restoration that 1) lacks long-term engagement and monitoring, 2) denies people use of lands (even Indigenous people who have been there for millennia), and 3) sets fixed ecological baselines or goals even for ecosystems which historically were highly managed and dynamic. They describe two use cases where management outcomes preferred by Indigenous people were ignored, instead managing for outcomes preferred by non-Indigenous ranchers or residents. They call for restorative justice being the norm, and ethical engagement with communities in each specific place (rather than coopting and misusing Indigenous knowledge). They also call for more openness to evolving needs and conditions of both people and ecosystems, and acknowledging failures and wrongdoing.<br /><br /><u><em>Bard summary:</em></u><br />This article is about pop-up restoration in colonial contexts. It discusses the problems with pop-up restoration, which is restoration that is done without Indigenous input and does not consider Indigenous knowledge. The authors argue that pop-up restoration can actually do more harm than good. They propose that instead, restoration should be done in collaboration with Indigenous communities and should center Indigenous knowledge.</p><p><br /><br /><strong>CARBON BENEFITS OF WORKING FROM HOME:</strong><br /><u><em>Jon summary:</em></u><br />Tao et al. 2023 is an article about carbon emissions when working from home vs in office (see <a data-cke-saved-href="https://wapo.st/46mc2cJ" href="https://wapo.st/46mc2cJ" target="_blank">this WaPo article</a> for more). They claim in the abstract remote workers can have a 58% lower carbon footprint than staff fully in the office, BUT there are a bunch of issues with the paper that make me think this claim is invalid (although I'm almost certain there are carbon benefits). First - the 58% number in the abstract does not appear anywhere in the paper (even the SI), the results say 54%. It's a small difference but seems sloppy which can be a warning sign. Next, the methods (even in the SI) do not really explain their calculations in full. They do not define the components of "office energy use" let alone how they measure and calculate it, which is bewildering (they seem to have modeled how attendance & headcount related to office actual energy use but that's about all I could figure out). As a result I can't assess the amount of energy related to occupancy vs. not (I presume heating and cooling are not affected unless there's enough remote workers to shrink the office building). Finally, two assumptions seem especially problematic. First is that residential heating, cooling, and (de)humidifying is OFF when staff are not at home. That is pretty rare for people who live in places w/ hot summers and/or cold winters. Second, the benefits they cite only come from seat sharing, not just people working at home and leaving their seat empty. That's a valid scenario to look at, but it undercuts the framing about benefits from working from home X days per week (and note that many offices want staff to be in on the same days, rather than rotate, which limits seat sharing). So I'm not convinced on their office energy estimates, but the avoided carbon from having fewer commutes is hard to argue with. The authors argue that people working remotely have more NON-commute travel though, so savings are less than you'd think. So let's keep talking about benefits of remote and hybrid work, but NOT assume that will dramatically shrink our carbon footprint of work.<br /><br /><u><em>Bard summary</em></u><em> (and note that it uncritically repeats the claim in the abstract - despite the paper not supporting it):</em><br />This is an article about the climate change mitigation effects of remote work. It discusses the environmental impacts of commuting, non-commute travel, office energy use, and residential energy use. Remote work can reduce up to 58% of the carbon footprint of work. The impacts of IT usage are negligible. The environmental benefits of remote work depend on proper configuration of lifestyle and workplace.</p><p><br /><br /><strong>CONNECTIVITY:</strong><br /><u><em>Jon summary:</em></u><br />Hanson et al. 2023 compares 8 approaches to optimally expand protected areas (PAs) for birds in Washington state that all consider connectivity differently (all spending $7.6 billion). Some are oblique (maximizing total protected area and presuming it will decrease mean distance between habitat), some focused on connectivity WITHIN PAs (minimizing edge / perimeter, which likely REDUCES connectivity between PAs so looks very different), and several with different assumptions about what conditions facilitate the most species movement (like focusing on connecting areas w/ relatively homogeneous cores and corridors). See Table 2 for pros and cons of each approach, and Fig 2 for maps comparing the results (blue is unique to that approach, yellow was included by all, orange was shared by at least two). There was no obvious winner, but the 'environmental similarity' approach scored pretty well on most. Note that land cost is a big driver of the results.<br /><br />For this one Bard said "I'm a text-based AI and can't assist with that." (or variants on this reply when I tried again). Seems to be an access issue since it still worked for the other articles here.</p><p><br /><br /><strong>LEARNING FROM FAILURE:</strong><br /><u><em>Jon summary:</em></u><br />Dickson et al. 2023 piqued my curiosity by breaking down different causes of conservation failure and how to respond. I generally dislike taxonomy papers, and find them academic and hard to apply. But understanding how to respond to different kinds of failure seems helpful, especially for the most common causes (including lacking a sufficiently robust theory of change. see table 2 for more). Their taxonomy has 59 (!) root causes, grouped into 6 categories: 1) planning, design, or knowledge (e.g., inadequate theory of change); 2) team dynamics (e.g., disagreements on what priorities should be); 3) project governance (e.g., lack of a technical advisory group); 4) resources (e.g., staff overloaded or lack needed technical expertise); 5) stakeholder relationships (e.g., lack of buy-in from gov't); and 6) unexpected external events (e.g., natural disaster, war, disease, etc.). After reading all the ways to fail, my main take away is that failure will happen sometimes and we need to focus on how to learn and pivot. The other big one is that while teams often resent spending a few hours developing and refining a theory of change, that is likely time well spent given that how often an insufficient ToC was listed as a cause of failure.<br /><br /><u><em>Bard summary:</em></u><br />This article is about introducing a common taxonomy to support learning from failure in conservation. It discusses the need for a culture shift in conservation towards learning from failure. It also details the development of a taxonomy of root causes of failure in conservation. The taxonomy is organized into three tiers: overarching cause categories, midlevel cause categories, and specific root causes. The authors tested the taxonomy by asking conservation practitioners to use it to classify the causes of failure for conservation efforts they had been involved in. The authors then analyzed the frequency that particular root causes were encountered by projects within this test sample. The authors suggest that the taxonomy could be used to improve the identification, analysis, and subsequent learning from failed conservation efforts.<br /><br /><br /><strong>REFERENCES:</strong><br />Dickson, I., Butchart, S. H. M., Catalano, A., Gibbons, D., Jones, J. P. G., Lee‐Brooks, K., Oldfield, T., Noble, D., Paterson, S., Roy, S., Semelin, J., Tinsley‐Marshall, P., Trevelyan, R., Wauchope, H., Wicander, S., & Sutherland, W. J. (2023). Introducing a common taxonomy to support learning from failure in conservation. Conservation Biology, 37(1), 1–15. https://doi.org/10.1111/cobi.13967<br /><br />Grenz, J., & Armstrong, C. G. (2023). Pop-up restoration in colonial contexts: applying an indigenous food systems lens to ecological restoration. Frontiers in Sustainable Food Systems, 7(September), 1–12. https://doi.org/10.3389/fsufs.2023.1244790<br /><br />Hanson, J. O., Vincent, J., Schuster, R., Fahrig, L., Brennan, A., Martin, A. E., Hughes, J. S., Pither, R., & Bennett, J. R. (2022). A comparison of approaches for including connectivity in systematic conservation planning. Journal of Applied Ecology, 59(10), 2507–2519. https://doi.org/10.1111/1365-2664.14251<br /><br />Tao, Y., Yang, L., Jaffe, S., Amini, F., Bergen, P., Hecht, B., & You, F. (2023). Climate mitigation potentials of teleworking are sensitive to changes in lifestyle and workplace rather than ICT usage. Proceedings of the National Academy of Sciences, 120(39), 2017. https://doi.org/10.1073/pnas.2304099120</p><p><br /><br />Sincerely,<br /> <br />Jon<br /><br />p.s. In the photo above, Kong is sleeping with his head on my lap, while I am resting my head on him. He is such a sweet and cuddly dog.</p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-17039147886910239372023-10-24T13:33:00.002-04:002024-01-25T11:49:32.363-05:00October 2023 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/53162655935/in/photolist-2oZNtD6-2oZNvs8-2oZNvst-2oZNNZL/" title="Giant anteater"><img alt="Giant anteater" height="225" src="https://live.staticflickr.com/65535/53162655935_283536ff76_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script>
<p><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">Greetings,</span></p><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">This month I have just two articles - one on conservation priorities (a longer than usual review) and one on how mining affects tropical rivers. I also forgot to post on this site for a few weeks, sorry!</span><div><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">If you know someone who wants to sign up to receive these summaries, they can do so at </span><a href="http://eepurl.com/diB0nr" style="background-color: white; color: #007c89; font-family: Helvetica; font-size: 16px; text-size-adjust: 100%;">http://b</a><a href="http://bit.ly/sciencejon" style="background-color: white; color: #007c89; font-family: Helvetica; font-size: 16px; text-size-adjust: 100%;" target="_blank">it.ly/sciencejon</a><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"> (no need to email me).</span><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><strong style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">CONSERVATION PRIORITIES:</strong><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><strong style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">Mair et al. 2021</strong><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"> proposes the use of a "species threat abatement and restoration (STAR)" metric with two scores. The threat abatement one for a location (START) sums up each threatened species present, with higher threat like Critically Endangered scoring higher, favoring locations with more species that are more threatened. The idea is to estimate effort to abate all threats (which seems unreasonable). The restoration score (STARR) divides 'restorable habitat' for all threatened species in a given pixel by global habitat for that species, and sums across species.</span><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">The paper calculates both for threatened terrestrial vertebrates. START results look pretty similar to range-size rarity scores for threatened species or a few other existing metrics, and suffer from the same issues (bias to data-rich places, lack of accurate info in many places). STARR seems more conceptually interesting but I'm pretty suspicious that the projected range maps are valid (given issues w/ current range maps) and since they didn't screen out any low-feasibility areas (like highly productive ag) it doesn't seem too useful. I also struggle to understand how they could have come up with the map in Fig 2b using the methods they describe. But that could be me being slow rather than a problem with the analysis.</span><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><strong style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">FRESHWATER</strong><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">:</span><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><strong style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">Dethier et al 2023</strong><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"> (briefly summarized in Walmsley 2023) finds that mining in tropical countries is dramatically increasing sediment in rivers. 80% of the 173 rivers affected by mining that they studied had sediment concentrations more than double what they were prior to mining. This is a pretty coarse estimate using satellite data, so the actual sediment estimates are very rough, but the general pattern should be valid.</span><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><strong style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">REFERENCES:</strong><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">Dethier, E. N., Silman, M., Leiva, J. D., Alqahtani, S., Fernandez, L. E., Pauca, P., Çamalan, S., Tomhave, P., Magilligan, F. J., Renshaw, C. E., & Lutz, D. A. (2023). A global rise in alluvial mining increases sediment load in tropical rivers. Nature, 620(7975), 787–793. https://doi.org/10.1038/s41586-023-06309-9</span><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">Mair, L., Bennun, L. A., Brooks, T. M., Butchart, S. H. M., Bolam, F. C., Burgess, N. D., Ekstrom, J. M. M., Milner-Gulland, E. J., Hoffmann, M., Ma, K., Macfarlane, N. B. W., Raimondo, D. C., Rodrigues, A. S. L., Shen, X., Strassburg, B. B. N., Beatty, C. R., Gómez-Creutzberg, C., Iribarrem, A., Irmadhiany, M., … McGowan, P. J. K. (2021). A metric for spatially explicit contributions to science-based species targets. Nature Ecology & Evolution, 5(6), 836–844. https://doi.org/10.1038/s41559-021-01432-0</span><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">Walmsley, B. (2023). Satellite images show the widespread impact of mining on tropical rivers. Nature, 620(7975), 729–730. https://doi.org/10.1038/d41586-023-02349-3</span><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">Sincerely,</span><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"> </span><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">Jon</span><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"> </span><br style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;" /><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">p.s. This is a photo of a giant anteater that I saw on a recent trip to the Pantanal in Brazil. If you're curious I have more </span><a href="https://www.flickr.com/photos/jaundicedferret/albums/72177720310946083" style="background-color: white; color: #007c89; font-family: Helvetica; font-size: 16px; text-size-adjust: 100%;" target="_blank">Pantanal photos</a><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;"> and </span><a href="https://www.youtube.com/playlist?list=PLlNtIaZ4Kzdp9Gd85nkFYgjGeTuhPhYyf" style="background-color: white; color: #007c89; font-family: Helvetica; font-size: 16px; text-size-adjust: 100%;" target="_blank">Pantanal videos</a><span style="background-color: white; color: #202020; font-family: Helvetica; font-size: 16px;">.</span></div>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-37655272912478622322023-08-01T08:43:00.001-04:002023-08-01T08:43:00.153-04:00August 2023 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/53031765541/in/datetaken/" title="Cardinal on blueberry cage"><img src="https://live.staticflickr.com/65535/53031765541_019d8bd8c9_w.jpg" width="400" height="225" alt="Cardinal on blueberry cage"/></a><script async src="//embedr.flickr.com/assets/client-code.js" charset="utf-8"></script>
<p>Hi,</p><p><br />I'm behind on science reading again but still have three articles to share. Two are on wildlife migrations, and one is on bullshit (really)!<br /><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a data-cke-saved-href="http://eepurl.com/diB0nr" href="http://eepurl.com/diB0nr">http://b</a><a data-cke-saved-href="http://bit.ly/sciencejon" href="http://bit.ly/sciencejon" target="_blank">it.ly/sciencejon</a> (no need to email me).<br /><br /><strong>BULLSHIT:</strong><br />Turpin et al 2021 finds that being able to produce satisfying and seemingly accurate bullshit ("communication characterised by an intent to be convincing or impressive without concern for truth") seems correlated with real intelligence (albeit using weak proxies of a 10-item vocabulary test, and ratings of how others perceived their intelligence from writing samples). See Fig 1 for how they rated how convincing bullshit was. Interestingly people who scored better on the vocab test were slightly less willing to bullshit, and people more willing to bullshit were less able to distinguish bullshit from meaningful info. So <u>a TL;DR could be that smarter people are less susceptible to bullshit, less willing to bullshit, but also better at bullshitting convincingly</u>. Hat tip to Patrick Beary for sending this. And in case you're thinking this is a one-off joke, another paper on bullshit I reviewed ("<a data-cke-saved-href="https://www.cambridge.org/core/journals/judgment-and-decision-making/article/on-the-reception-and-detection-of-pseudoprofound-bullshit/0D3C87BCC238BCA38BC55E395BDC9999" href="https://www.cambridge.org/core/journals/judgment-and-decision-making/article/on-the-reception-and-detection-of-pseudoprofound-bullshit/0D3C87BCC238BCA38BC55E395BDC9999" target="_blank">On the reception and detection of pseudo-profound bullshit</a>") has 597 citations!<br /><br /><strong>WILDLIFE MIGRATION</strong>:<br />Remember the 'lockdown' in the early days of COVID where people were asked to stay at home as much as possible, and traffic and even people walking around plummeted? Tucker et al. 2023 looks at how that impacted 43 species of mammals around the world. They found it varied a ton, but that in the short term (hour to hour) animals moved a bit less (presumably from less trying to avoid people). They found longer-term movement (10-day distance) only changed for coutnries with the strictest lockdowns like Italy and France, and Fig 3a makes it clear that while that change is significant it's dwarfed by the variation in effect. The findings on roads are not significant at the individual level and the effects they're reporting don't seem very compelling so I'm leaving those out. There's a Washington Post article about this paper here which includes some stories about some of the more adventurous animals: https://wapo.st/4660hHW<br /><br />Young et al. 2023 monitored wildlife crossings along the Toowoomba Bypass in eastern Australia and found they were mostly used by non-native animals like feral cats, European redfoxes, and European hares (as well as dingoes). They also compared wildlife presence and density to adjacent bushland; only 61% of all the species they found were detected at crossings at all. The only difference they saw between viaducts, culverts, and underpasses was that swamp wallabies and hares both preferred the viaduct.<br /><br /><strong>REFERENCES:</strong></p><p>Tucker, M. A., Schipper, A. M., Adams, T. S. F., Attias, N., Avgar, T., Babic, N. L., Barker, K. J., Bastille-Rousseau, G., Behr, D. M., Belant, J. L., Beyer, D. E., Blaum, N., Blount, J. D., Bockmühl, D., Pires Boulhosa, R. L., Brown, M. B., Buuveibaatar, B., Cagnacci, F., Calabrese, J. M., … Mueller, T. (2023). Behavioral responses of terrestrial mammals to COVID-19 lockdowns. Science, 380(6649), 1059–1064. https://doi.org/10.1126/science.abo6499<br /><br />Turpin, M. H., Kara-Yakoubian, M., Walker, A. C., Walker, H. E. K., Fugelsang, J. A., & Stolz, J. A. (2021). Bullshit Ability as an Honest Signal of Intelligence. Evolutionary Psychology, 19(2), 1–10. https://doi.org/10.1177/14747049211000317<br /><br />Young, G., King, R., & Allen, B. L. (2023). Where do wildlife cross the road? Experimental evaluation reveals fauna preferences for multiple types of crossing structures. Global Ecology and Conservation, e02570. https://doi.org/10.1016/j.gecco.2023.e02570<br /><br />Sincerely,<br /> <br />Jon<br /> <br />p.s. After the birds ate every single blueberry I grew last year, I built a cage this year w/ gaps big enough to let some pollinators in but keep birds out (until we harvested enough and let them have the last of them). They periodically would check for gaps, and twice robins managed to squeeze in and get stuck until I let them out. I'll improve the design next year.</p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-77255802594661656792023-07-03T08:30:00.003-04:002023-07-03T08:30:00.146-04:00July 2023 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/52917192640/" title="Little mermaid food"><img alt="Little mermaid food" height="225" src="https://live.staticflickr.com/65535/52917192640_a7fbea928d_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script> <div>Greetings,<br /><br />This month I have two articles on climate resilience, one on climate mitigation, and one on science-implementation partnerships. Plus a couple articles on AI as usual.<br /><br />While it's a Canadian science fair project and not peer-reviewed science, I was interested to see this <a data-cke-saved-href="https://csfjournal.com/volume-1-issue-1/fruitflies" href="https://csfjournal.com/volume-1-issue-1/fruitflies" target="_blank">test of "you catch more flies with honey than vinegar.</a>" The experiment found that you catch more flies with honey <u>and </u>vinegar than with vinegar alone, which catches more than honey alone. But bringing it back to the saying: please don't be a jerk regardless.<br /><br />My obligatory article on AI (and specifically Large Language Models [LLMs] like ChatGPT) is extra-fascinating this month. Can (and should) LLMs help us communicate more empathically? Check out this NY times article '<a data-cke-saved-href="https://www.nytimes.com/2023/06/12/health/doctors-chatgpt-artificial-intelligence.html?unlocked_article_code=24hawY1JMfY1-tY_-mpfEdeFOWqXUwaei_OLKIs3pEEXHqEsY_dB9MpZ5C0k2iHMDsUrCa6EGJuQuLAXsJlVqh_ImGUucRGLMjWlKmZkekXQfxv_-uQ5-Zw6QKt9v71KcEFP3SN2GbYfg9CtXZDCc_hgKFzIFH7f3wTBGhj35RqDyQ1uK_I8k0ngALpJgj493Y66KTeN8BdSM8bw-uV5xk6s2Jeh_7-qY9hHV_40l-_-5ET0SK5q3qQBJ9lOggGnpInh_nAHj-5uq7dfqkP3SCvR7gWzBliUvbcYONiXelhwJ9uS2BEYDD5Z1ykD663MbwP4dGVQE1NmhV_2w7cIUecGrfYvFkZUg5a10KFPBNw&smid=url-share" href="https://www.nytimes.com/2023/06/12/health/doctors-chatgpt-artificial-intelligence.html?unlocked_article_code=24hawY1JMfY1-tY_-mpfEdeFOWqXUwaei_OLKIs3pEEXHqEsY_dB9MpZ5C0k2iHMDsUrCa6EGJuQuLAXsJlVqh_ImGUucRGLMjWlKmZkekXQfxv_-uQ5-Zw6QKt9v71KcEFP3SN2GbYfg9CtXZDCc_hgKFzIFH7f3wTBGhj35RqDyQ1uK_I8k0ngALpJgj493Y66KTeN8BdSM8bw-uV5xk6s2Jeh_7-qY9hHV_40l-_-5ET0SK5q3qQBJ9lOggGnpInh_nAHj-5uq7dfqkP3SCvR7gWzBliUvbcYONiXelhwJ9uS2BEYDD5Z1ykD663MbwP4dGVQE1NmhV_2w7cIUecGrfYvFkZUg5a10KFPBNw&smid=url-share" target="_blank">When Doctors Use a Chatbot to Improve Their Bedside Manner</a>.' I <em>love </em>the idea of someone wanting to be kind by using the right words, not knowing what to say, and getting help with that. I have found it's very common for people to stay silent when they can't find 'the right words' around illness and death and grief, so I am all for helping people (including doctors) to get unstuck. I asked Bard (Google's LLM) for advice on how to support a friend who is grieving and found it mostly excellent. Not ideal but really good and something most of us could learn from. The idea of machines helping us to express empathy more effectively is so intriguing and I'm all for it.<br /><br />The latest AI tool I tried out is "<a data-cke-saved-href="https://www.chatpdf.com/" href="https://www.chatpdf.com/" target="_blank">ChatPDF</a>" which lets you upload a PDF and ask the tool questions about it. It works pretty well for some things, but is oddly dull in others. Like for one paper I asked it which species was responsible for most of the primary effect they reported (t CO2e of climate mitigation) and it didn't know. But when I asked it what the contribution was of the species I knew drove >80% of the effect, it reported it numerically. Apparently it was unable to divide the number it knew for the species in question by the total effect size number (which it also knew). But I thought it performed reasonably well with my questions about the IPCC report. TL;DR is that it seems better at finding / extracting info than any kind of reasoning.<br /><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a data-cke-saved-href="http://eepurl.com/diB0nr" href="http://eepurl.com/diB0nr">http://b</a><a data-cke-saved-href="http://bit.ly/sciencejon" href="http://bit.ly/sciencejon" target="_blank">it.ly/sciencejon</a> (no need to email me).<br /><br /><br /><strong>CLIMATE MITIGATION:</strong><br />Duncanson et al. 2023 estimates how much global forested protected areas may be reducing climate change. They matched forested protected areas to similar forested unprotected areas using data from 2000 (land cover, ecoregion, and biome; with additional control pixels that accounted for population etc. - see Table S1). Then they used the new (2019) GEDI lidar data to estimate aboveground forest biomass in 2020. 63% of forested PAs had significantly higher biomass than matched unprotected areas; on average PAs have 28% more aboveground biomass. Over a third of that effect globally comes from Brazil; Africa had less C dense forests and more human pressures on both PAs and unprotected areas. As you'd guess, most of the difference in unprotected sites was due to deforestation. But in 18% of PAs carbon was higher than unprotected sites even though optical sensors didn't detect deforestation (implying LiDAR is detecting either avoided degradation and/or enhanced growth in PAs). As a final note, <a data-cke-saved-href="https://www.sciencedirect.com/science/article/pii/S0034425721002911" href="https://www.sciencedirect.com/science/article/pii/S0034425721002911" target="_blank">other research has shown that both ICESat-2 and GEDI LiDAR satellites </a><a data-cke-saved-href="https://www.sciencedirect.com/science/article/pii/S0034425721002911" href="https://www.sciencedirect.com/science/article/pii/S0034425721002911" target="_blank">tend to underestimate forest canopy heights</a> (mostly irrelevant here given the matching approach, but good to know for other global estimates).<br /><br /><br /><strong>CLIMATE RESILIENCE:</strong><br />Anderson et al. 2023 is the latest paper supporting the data in The Nature Conservancy's Resilient Land Mapping Tool (https://maps.tnc.org/resilientland/). They looked for overlap in three layers across the US: biodiversity value (the union of TNC's ecoregional priority areas), resilient sites (places with diverse and connected microclimates), and 'climate flow' (a circuit theory analysis of where wildlife is likely to shift in response to climate change). See Fig 1 for their main results, or the web map is better since you can separate out the three main layers. The way 'biodiversity value' was assessed varies a lot by ecoregion, and some are more ambitious than others (e.g., the biggest biodiversity patch is in the Nebraska Sandhills, but other ecoregions also have some big blocks of intact habitat). So not every green blob is equally high-priority, but collectively it does have representation across all ecoregions which is good. On the main map, both blue and dark green blobs offer the most value for climate resilience, but again the web map lets you see the continuous data.<br /><br />Rubenstein et al. 2023 is a systematic review of how documented range shifts (by plants and animals, presumably in response to climate change) compare to predictions. Across 311 papers, only 47% of shifts due to temperature were in expected directions (higher latitudes & elevations, and marine movement to deeper depths was seen but was non-significant). See Fig 4 for how results varied by taxonomic group, ecoystem type, and type of shift. Not many studies looked at precip but of those that did only 14% found species moving to stay in a precip niche. Note: this means simple assumptions of how species will move are of limited value, but NOT that local or regional predictions are inherently flawed. The authors note that considering local predictions of changing temp and precip will often depart from these simple assumptions, and other factors like water availability, fire, etc. are likely to be relevant. A final note on the last page was helpful: not all range shifts have equal relevance to management. In some cases a few individuals are moving to new places but most of the wildlife population doesn't shift at all. Both shifts AND non-shifts have implications for how management should change to keep species and ecosystems healthy! This paper has a LOT of nuance and variation in this paper, and a very detailed methods section with good recommendations for how scientists should continue these investigations. <br /><br /><br /><strong>SCIENCE-IMPLEMENTATION PARTNERSHIPS:</strong><br />Carter et al. 2020 is a call for better coordination of science across landscapes in the Western US to better inform land management. They walk through 5 examples of how it has worked (standard monitoring for national parks, tools to help restore arid & semi-arid landscapes, predictive soil maps of where reclaiming disturbed land could work, frameworks for sage-grouse monitoring, and targeted interventions to improve big-game connectivity). They ask agencies to better support boundary-spanning partnerships w/ scientists, and to make more specific asks to scientists about what information they need. I'm not convinced that's likely; White et al. 2019 and others have found land managers don't always see science as a key input, they're often too busy to even know where they need help, and a high-engagement partnership may not always be the best pitch to agency staff who are stretched thin.<br /><br /><br /><strong>REFERENCES:</strong><br />Anderson, M. G., Clark, M., Olivero, A. P., Barnett, A. R., Hall, K. R., Cornett, M. W., Ahlering, M., Schindel, M., Unnasch, B., Schloss, C., & Cameron, D. R. (2023). A resilient and connected network of sites to sustain biodiversity under a changing climate. Proceedings of the National Academy of Sciences, 120(7), 1–9. https://doi.org/10.1073/pnas.2204434119<br /><br />Carter, S. K., Pilliod, D. S., Haby, T., Prentice, K. L., Aldridge, C. L., Anderson, P. J., Bowen, Z. H., Bradford, J. B., Cushman, S. A., DeVivo, J. C., Duniway, M. C., Hathaway, R. S., Nelson, L., Schultz, C. A., Schuster, R. M., Trammell, E. J., & Weltzin, J. F. (2020). Bridging the research-management gap: landscape science in practice on public lands in the western United States. Landscape Ecology, 35(3), 545–560. https://doi.org/10.1007/s10980-020-00970-5<br /><br />Duncanson, L., Liang, M., Leitold, V., Armston, J., Krishna Moorthy, S. M., Dubayah, R., Costedoat, S., Enquist, B. J., Fatoyinbo, L., Goetz, S. J., Gonzalez-Roglich, M., Merow, C., Roehrdanz, P. R., Tabor, K., & Zvoleff, A. (2023). The effectiveness of global protected areas for climate change mitigation. Nature Communications, 14(1), 2908. https://doi.org/10.1038/s41467-023-38073-9<br /><br />Rubenstein, M. A., Weiskopf, S. R., Bertrand, R., Carter, S. L., Comte, L., Eaton, M. J., Johnson, C. G., Lenoir, J., Lynch, A. J., Miller, B. W., Morelli, T. L., Rodriguez, M. A., Terando, A., & Thompson, L. M. (2023). Climate change and the global redistribution of biodiversity: substantial variation in empirical support for expected range shifts. Environmental Evidence, 12(1), 7. https://doi.org/10.1186/s13750-023-00296-0<br /><br /><br /><br />Sincerely,<br /> <br />Jon<br /><br /><p>p.s. The photo is of food we made for a little mermaid party, including crab cupcakes (no crab in them, they were vegan), mermaid tail ice cream cones, sugar cookies, and veggie sushi </p></div>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-57820230562555863582023-06-01T08:07:00.011-04:002023-06-01T08:07:00.140-04:00June 2023 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/52822440594/" title="Space pansies"><img alt="Space pansies" height="225" src="https://live.staticflickr.com/65535/52822440594_96f23942fe_w.jpg" width="400" /></a><p>Greetings,<br /><br /><br />I haven't had much time to read science this month, so I'm just sharing a newspaper article about AI training, and one science article along w/ alternative summaries of it to highlight Bing chat options.<br /><br />This is a fascinating article about which web sites AI tools are trained on, and what that implies for their accuracy, bias, etc. <br /><a data-cke-saved-href="https://wapo.st/42ULddK" href="https://wapo.st/42ULddK" target="_blank"><u>https://wapo.st/42ULddK</u></a><br />When I asked ChatGPT "What are the most critical weaknesses of ChatGPT" one answer was 'Bias in Training Data: The training data used to develop ChatGPT is sourced from the internet and can contain biases, inaccuracies, and offensive content. This can lead to the model reproducing and amplifying these biases in its responses.'</p><p>Another good read comes from the New York Times, with detail about how <a href="https://www.nytimes.com/2023/05/01/business/ai-chatbots-hallucination.html?unlocked_article_code=wJZmcdtDnoOqEYbjIxg2FjajHfnX9B1JfSObWkszpflvmW1yNkELWqTkm0UN-5yPl_NaXk7nHp7W5hHpqnJsl7W1_Hp_Dy0y2_dxBC-IVsIG9Xv_AAJ1mu0AiKNS91eoBzRPyQMK_XWTpGfPmZZ8aJK-7wdIdPaXldtEd5IzkqlhJ5bduCBhlwTzGMSILwmqwVgX4bU0kgTWyNJXc4HlR7pg6X-cm8IHL1tA-gqeNndOou2UB_EZ_80JAbRN9icWjhClNaSBqmAmx3uPyRph1GcwvhG-1jgVI8V86_IVGq_bUjn0ocrav4Lm_VlvCJD_bliUSp5qsqcSzzDKrwIJjtmO4Qo&smid=url-share">chatbots regularly completely fabricate untrue information (or 'hallucinate')</a>. It's an important read if you ever ask chatbots for what you hope is factual information. How bad can the fabrications be? They have <a href="https://www.washingtonpost.com/technology/2023/04/05/chatgpt-lies/ ">falsely accused people of sexual harassment and bribery</a>, pointing to non-existent sources.</p><p><br />For those who haven't used it yet, Bing's version of ChatGPT has some nice features, namely 1) it provides actual references by default (the normal ChatGPT will provide references upon request, but they often don't have the info ChatGPT provided), 2) you can switch between 'creative' or 'precise' or 'balanced' response styles (I include examples below). To try it out, open Microsoft Edge (it won't work in other browsers), do a search on bing.com, and right below the search box click "Chat" to the right of "Search". Note that as per the article above, the references may still be false!<br /><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a data-cke-saved-href="http://eepurl.com/diB0nr" href="http://eepurl.com/diB0nr">http://b</a><a data-cke-saved-href="http://bit.ly/sciencejon" href="http://bit.ly/sciencejon" target="_blank">it.ly/sciencejon</a> (no need to email me).<br /><br /><strong>SCIENCE COMMUNICATIONS:</strong><br />Toomey et al. 2023 is a nice reminder that just sharing information doesn't usually change minds. They challenge the idea that facts & scientific literacy lead to research being applied, and that broad communications targeting as many individuals as possible are the most effective way to share those facts. Instead they recommend appealing to values and emotions, and strategically targeting audiences by considering social networks (drawing on science about behavior change) and social norms. I love the conclusion that "this article may not change your mind" but that they hope it will inspire reflection. I also like the use of the backronym WEIRD (Western, Educated, Industrialized, Rich, Democratic) to describe countries like the US.<br /><br />Here's a <strong>Bing AI summary </strong>using the "<strong>precise</strong>" option (99 words):<br />'The paper “Why facts don’t change minds: Insights from cognitive science for the improved communication of conservation research” discusses four common myths about how to best communicate science for decision-making. These myths are: that facts change minds, scientific literacy will lead to enhanced research uptake, individual attitude change will shift collective behaviors, and broad dissemination is best. The article provides four alternative insights that can support effective science communication and impact: engaging the social mind for optimal decision-making, understanding the power of values, emotions, and experience in swaying minds, changing collective behavior, and thinking strategically for biggest impact.'<br /><br />Here's a <strong>Bing AI summary </strong>using "<strong>creative</strong>" (262 words):<br />'The article argues that conservation scientists need to update their models of science communication and behavioral change based on insights from cognitive science. It challenges four common myths about how to best communicate science for decision-making, and provides four alternative insights that can support effective science communication and impact. The myths and insights are:<br />• <strong>Myth</strong>: Facts change minds. <strong>Insight</strong>: Engage the social mind for optimal decision-making. The article explains that humans are social animals who rely on their peers and trusted sources for information, and that facts alone are not enough to persuade people who have strong prior beliefs or identities.<br />• <strong>Myth</strong>: Scientific literacy will lead to enhanced research uptake. <strong>Insight</strong>: Understand the power of values, emotions, and experience in swaying minds. The article shows that people tend to filter information based on their values, emotions, and personal experiences, and that scientific literacy does not necessarily lead to more rational or pro-environmental choices.<br />• <strong>Myth</strong>: Individual attitude change will shift collective behaviors. <strong>Insight</strong>: Change collective behavior by targeting social norms and networks. The article suggests that individual attitudes are often influenced by social norms and networks, and that changing collective behavior requires understanding and leveraging these social factors.<br />• <strong>Myth</strong>: Broad dissemination is best. <strong>Insight</strong>: Think strategically for biggest impact. The article advises that conservation scientists should be more strategic and selective in their communication efforts, and focus on the most relevant and influential audiences, messages, and channels.<br />The article concludes by calling for more interdisciplinary collaboration between conservation scientists and cognitive scientists to design and evaluate effective science communication interventions for conservation impact.'<br /><br />Note I started w/ "balanced" but found it the least useful of the three so am skipping it here.<br /><br /><br /><strong>REFERENCES:</strong><br />Toomey, A. H. (2023). Why facts don’t change minds: Insights from cognitive science for the improved communication of conservation research. Biological Conservation, 278(December 2022), 109886. https://doi.org/10.1016/j.biocon.2022.109886<br /><br />Sincerely,<br /> <br />Jon<br /> p.s. These 'space pansies' always make me think my elevated planter has somehow become sci-fi whenever I walk by</p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-91313073701462943282023-05-01T08:24:00.001-04:002023-05-01T08:24:00.136-04:00May 2023 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/52723859270/in/datetaken/" title="Nut Case by Katie Hudnall"><img alt="Nut Case by Katie Hudnall" height="225" src="https://live.staticflickr.com/65535/52723859270_d1405cbab6_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script>
<br /><div><br /></div><div>Greetings,<br /><br /><a data-cke-saved-href="https://www.washingtonpost.com/climate-environment/interactive/2023/spring-early-late-climate-change/" href="https://www.washingtonpost.com/climate-environment/interactive/2023/spring-early-late-climate-change/" target="_blank">Does spring feel like it came early or late</a>? It's not just you! DC leafed out 3 weeks ahead of schedule.<br /><br />This month is a bit of a grab bag: three papers on fishery management, one on assisted migration for wildlife, one on forests & fire, and one on the role of wildlife in climate mitigation that I found pretty misleading.<br /><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a data-cke-saved-href="http://eepurl.com/diB0nr" href="http://eepurl.com/diB0nr">http://b</a><a data-cke-saved-href="http://bit.ly/sciencejon" href="http://bit.ly/sciencejon" target="_blank">it.ly/sciencejon</a> (no need to email me).<br /><br /><strong>CLIMATE CHANGE & WILDLIFE:</strong><br />Schmitz et al. 2023 makes a fair point but uses some egregious estimates to do so (please don't trust the estimated climate mitigation benefits). They argue that the role of animals in boosting carbon sequestration (and/or reducing soil carbon and methane emissions) in underappreciated, and they may be right. Fig 1 is a cool thought experiment looking at potential impacts of boosting animal populations in different case studies. BUT the estimate of a huge 6.41 additional Gt CO2e / yr that could be reduced via animals is based on some really weak assumptions. For example, 86% of that 6.41 Gt comes from marine fish (5.5 Gt / yr). But that 5.5 Gt comes from another report, and is actually an estimate of CURRENT fish carbon flux (not potential to increase additional sequestration via conservation) recognizing a ton of uncertainty. Their bison estimate (another 9% of the 6.41 Gt) assumes that bison start grazing ungrazed lands when in fact they'd be displacing cattle in most cases (and one of the papers they cite lists the C benefit of cattle and bison as about the same). The only other animal with a substantial contribution is grey wolves (4% of total), and it's based on a single study on net primary productivity in Michigan which ignores the albedo effect. So overall, this study starts with decent evidence but makes some really flawed assumptions about how to translate them into global climate mitigation potential.<strong><br /><br /><br />WILDLIFE AND ASSISTED MIGRATION:</strong><br />Fitzpatrick et al. 2023 looks at the potential for assisted migration (moving individual animals to different habitats, sometimes along w/ targeted captive breeding) as a form of 'genetic rescue' to restore gene flow across fragmented federally listed vertebrate populations in the US via assisted migration. They gave 222 spp a score from -1->4, with 2/3 of spp scoring 2 or higher (and thus may be candidates for assisted migration, see Fig 1b for results by type of animal, or Fig 2 for example candidate spp). Only 5% of spp. had a management plan mentioning "genetic rescue" (or the general concept), but 44% of candidate species had already used assisted migration (more frequent in fishes and mammals)). Note that italicized words are in a glossary at the end. Also note this paper does NOT include other connectivity strategies like habitat restoration, wildlife crossings, etc.<br /><br /><br /><strong>FORESTS & FIRE</strong>:<br />Prichard et al. 2021 is a review of several questions related to fire in US western forests (see Table 1 for the summary of questions & answers). They include whether and when/ how to use cutting trees and prescribed burns as tools for reducing wildfire risk and/or climate mitigation and/or ecological restoration. The authors argue that many dry forests (and some moist forests mixed into dry forest landscapes) historically experienced more frequent fires of low to moderate intensity (often set by Native Americans), but that these forests are now denser and more likely to have severe crown fires (especially as summers become warmer and drier). That in turn will cause some forests to be lost and shift to grasslands or other ecosystems. Read Table 1 for key takeaways, including that for many (not all) Western forests, thinning and prescribed burning are important tools. Side note: given the active debate on this topic, I asked for input from a few forest scientists deep in the lit, and they recommended this article.<br /><br /><br /><strong>FISHERY MANAGEMENT</strong>:<br />Cinner et al. 2019 is a 16 year study of rotational fishing / closure in Papua. They found success in compliance with the system (due to strong social cohesion driven by leaders sharing info, a "carrot and stick" approach, and lots of community participation) BUT even though closed areas rebounded, over the study period fish biomass dropped by about half. So even though the closure program worked as intended, it wasn't enough to offset overfishing when areas were open.<br /><br />Cinner et al. 2012 is a study of 42 co-management arrangements for coral-dependent fisheries across 5 countries. Co-management led to more biomass than non-locally managed fished areas, and less than no-take closures (Fig 3). But see Fig 4 for key results (fish biomass was higher when markets were farther, and lower when more people replied on fishing for their primary income). They found just 54% of resource users saw co-management as improving their livelihoods (it seemed to benefit wealthier fishers w/ longer history of co-management and more agency).<br /><br />Hughes et al. 2012 looks at how vulnerable different countries are to declining coral-dependent fisheries leading to reduced food security. Tables 2-4 have ratings of 27 countries vulnerability to declining fisheries impacting food security, as well as ratings of assets, flexibility, learning, and social organization. The most vulnerable countries are Indonesia, Liberia, Ivory Coast, and Kenya.<br /><br /><br /><strong>REFERENCES:</strong><br />Cinner, J. E., McClanahan, T. R., MacNeil, M. A., Graham, N. A. J., Daw, T. M., Mukminin, A., Feary, D. A., Rabearisoa, A. L., Wamukota, A., Jiddawi, N., Campbell, S. J., Baird, A. H., Januchowski-Hartley, F. A., Hamed, S., Lahari, R., Morove, T., & Kuange, J. (2012). Comanagement of coral reef social-ecological systems. Proceedings of the National Academy of Sciences, 109(14), 5219–5222. https://doi.org/10.1073/pnas.1121215109<br /><br />Cinner, J. E., Lau, J. D., Bauman, A. G., Feary, D. A., Januchowski-Hartley, F. A., Rojas, C. A., Barnes, M. L., Bergseth, B. J., Shum, E., Lahari, R., Ben, J., & Graham, N. A. J. (2019). Sixteen years of social and ecological dynamics reveal challenges and opportunities for adaptive management in sustaining the commons. Proceedings of the National Academy of Sciences, 116(52), 26474–26483. https://doi.org/10.1073/pnas.1914812116<br /><br />Fitzpatrick, S. W., Mittan-Moreau, C., Miller, M., & Judson, J. M. (2023). Genetic rescue remains underused for aiding recovery of federally listed vertebrates in the United States. Journal of Heredity, March, 1–13. https://doi.org/10.1093/jhered/esad002<br /><br />Hughes, S., Yau, A., Max, L., Petrovic, N., Davenport, F., Marshall, M., McClanahan, T. R., Allison, E. H., & Cinner, J. E. (2012). A framework to assess national level vulnerability from the perspective of food security: The case of coral reef fisheries. Environmental Science & Policy, 23, 95–108. https://doi.org/10.1016/j.envsci.2012.07.012<br /><br />Prichard, S. J., Hessburg, P. F., Hagmann, R. K., Povak, N. A., Dobrowski, S. Z., Hurteau, M. D., Kane, V. R., Keane, R. E., Kobziar, L. N., Kolden, C. A., North, M., Parks, S. A., Safford, H. D., Stevens, J. T., Yocom, L. L., Churchill, D. J., Gray, R. W., Huffman, D. W., Lake, F. K., & Khatri‐Chhetri, P. (2021). Adapting western North American forests to climate change and wildfires: 10 common questions. Ecological Applications, 31(8). https://doi.org/10.1002/eap.2433<br /><br />Schmitz, O. J., Sylvén, M., Atwood, T. B., Bakker, E. S., Berzaghi, F., Brodie, J. F., Cromsigt, J. P. G. M., Davies, A. B., Leroux, S. J., Schepers, F. J., Smith, F. A., Stark, S., Svenning, J.-C., Tilker, A., & Ylänne, H. (2023). Trophic rewilding can expand natural climate solutions. Nature Climate Change. https://doi.org/10.1038/s41558-023-01631-6<br /><br />Sincerely,<br /> <br />Jon<br /> <br /><p>p.p.s. The photo is of a piece at the Renwick gallery in DC. The caption says: 'A mature oak tree produces about two thousand acorns a year, but only one in ten thousand acorns reaches maturity. Hudnall explains, “I think the idea of constant, repeated, tiny attempts for success, with the understanding that most will go nowhere, became a way for me to think about slow progress toward health in my own life.” '</p></div>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-57310533531443498372023-04-03T08:15:00.006-04:002023-04-03T08:15:00.217-04:00April 2023 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/50363410551/in/photolist-4bU3Y4-5xhwmM-277VDFx-4bY3yd-4cypgV-JQK3Sa-JQK43k-25JDEy1-2i7aa48-2i7b9Vw-2i7bas8-2ia3mfz-2iJTuHW-2jBzWLY-2jBDot1-2jJrDjF-2jRAGAn-2kcg5mE" title="Snake"><img alt="Snake" height="400" src="https://live.staticflickr.com/65535/50363410551_2277db90e6_w.jpg" width="300" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script>
<p data-pm-slice="1 1 []">Hello,<br /><br />In case you missed it last month, check out the paper I co-authored on gender equity (I repeated the summary below, <a href="https://bit.ly/TNCgenderpaper" tabindex="-1" target="_blank">read or skim the whole paper</a> if you have time, or at least read this <a href="https://blog.nature.org/science-brief/gender-bias-holds-women-back-in-conservation-careers/" tabindex="-1" target="_blank">blog overview</a><span style="text-decoration-line: underline;">)</span>.<br /><br />The IPCC's latest synthesis report came out recently (and I have a short summary below), so the need to do more on climate change is on my mind.</p><p></p><p>Want to work on climate change via energy modernization at Pew? We're hiring for three jobs right now on a team that I'm super excited about. If you have any questions and/or may be interested please take a look at the posts and then let me know if you want to know more (and please pass them on): </p><ol><li><p>Senior Officer, Clean Grid and Energy</p><p>https://pewtrusts.wd5.myworkdayjobs.com/TrustsExternal/job/Washington-DC-901-E/Senior-Officer--Clean-Grid---Energy_R002036 </p></li><li><p>Officer, State Campaigns</p><p>https://pewtrusts.wd5.myworkdayjobs.com/TrustsExternal/job/Washington-DC-901-E/Officer--State-Decarbonization-Campaign-Lead_R002067 </p></li><li><p>Senior Associate, State Campaigns </p><p>https://pewtrusts.wd5.myworkdayjobs.com/TrustsExternal/job/Washington-DC-901-E/Senior-Associate--State-Decarbonization-Campaigner_R002086</p></li></ol><p><br />Also - recently I am playing less w/ AI and reading more science myself, but thought this was a nice <a href="https://www.theverge.com/2023/3/24/23653377/ai-chatbots-comparison-bard-bing-chatgpt-gpt-4" tabindex="-1" target="_blank">overview of strengths and weaknesses between ChatGPT, Bing, and Bard</a>.</p><p><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a href="http://eepurl.com/diB0nr" tabindex="-1">http://b</a><a href="http://bit.ly/sciencejon" tabindex="-1" target="_blank">it.ly/sciencejon</a> (no need to email me).<br /></p><p></p><p><strong>CLIMATE CHANGE (IPCC report):</strong></p><p>The <strong>IPCC's latest report </strong>(<a href="https://www.ipcc.ch/report/ar6/syr/" tabindex="-1" target="_blank">the AR6 synthesis</a>) recently became available (here’s a direct link to the <a href="https://report.ipcc.ch/ar6syr/pdf/IPCC_AR6_SYR_SPM.pdf" tabindex="-1" target="_blank">36 page summary for policy makers</a>). If you've been following all the IPCC reports, there is no new info here. But there is a persistent thread of clarity that I found helpful. Of the many findings, the ones that stood out to me are:</p><ol><li><p><strong>The planet has warmed 1.1 degrees C already </strong>(1.6C on land)</p></li><li><p>The world is currently roughly <strong>on track for 3.2 C of warming </strong>based on implemented policies (Fig SPM5a, w/ range from 2.2C to 3.5C).</p></li><li><p>Good news - that means that <strong>"business as usual" is a little worse than RCP4.5 </strong>(Intermediate Emissions), ranging from Working Group III scenarios C5 to C7 (C7=High GHG emissions or SSP3-7.0). The <strong>high emissions (RCP8.5) scenario is pretty unlikely </strong>since it would require emissions to go up substantially over what is predicted. See Table 1 in Box SPM.1 for details.</p></li><li><p>Bad news - look more closely at Fig SPM5a. The <strong>paths to limit warming to 2C or 1.5C assume sharp cuts starting in 2020</strong>, which means even <strong>if we act immediately, cuts would have to be much sharper </strong>to make those pathways feasible (the report notes the lack of both commitments and financing). We should still make the attempt, but remember there is no magic binary threshold, and every bit of warming we avoid has real value.</p></li><li><p>They project climate impacts on species loss, human health, and food production (see Figure SPM3). </p></li></ol><p></p><p>I was struck by two quotes in particular:</p><p>“Adaptation options that are feasible and effective today [JF reminder - elsewhere they note: "‘today’ refers to 2019"] will become constrained and less effective with increasing global warming.”</p><p>“All global modelled pathways that limit warming to 1.5°C (>50%) with no or limited overshoot, and those that limit warming to 2°C (>67%), involve rapid and deep and, in most cases, immediate greenhouse gas emissions reductions in all sectors this decade.” (again, immediate relative to 2019). </p><p></p><p>The <a href="https://ipcc.ch/report/ar6/syr/downloads/press/IPCC_AR6_SYR_PressRelease_en.pdf" tabindex="-1" target="_blank">press release</a> also notes that "Emissions should be decreasing by now [JF - again, that's 2019] and will need to be cut by almost half by 2030, if warming is to be limited to 1.5°C." This <a href="https://www.pewtrusts.org/en/research-and-analysis/articles/2023/03/21/climate-action-needed-now-to-stave-off-catastrophic-impacts" tabindex="-1" target="_blank">blog post </a>highlights existing progress and what we need to do next.</p><p></p><p>AI side note: I asked Google Bard (their new beta AI) "What does the latest IPCC synthesis report say is the most likely amount of warming the world will experience?" and got a wrong answer: "<em>The latest IPCC synthesis report says that the most likely amount of warming the world will experience is 1.5 degrees Celsius above pre-industrial levels</em>.” (along with other text). But when I asked Bard "How much has the earth warmed so far, according to the latest IPCC synthesis report" it correctly states: "<em>According to the latest IPCC synthesis report, the Earth has warmed by 1.1 degrees Celsius (2 degrees Fahrenheit) since the start of the industrial era.</em>"</p><p></p><p></p><p><strong>CLIMATE CHANGE (other):</strong></p><p>Pearson et al. 2023 investigate whether restoring whale populations is likely to have a significant impact on climate mitigation. The idea being evaluated is that beyond carbon stored in whales themselves (which ends up in the deep sea when they die), that their poop stimulates a lot of phytoplankton growth which leads to net carbon capture (see Fig 1). The TL;DR results: whales and their poop MAY provide climate mitigation benefits but: we don't know yet, it'll take a long time to know, and additionality may be low (so don't sell whale carbon credits, please). See Box 1 for concerns w/ whale carbon credits, and box 2 for outstanding questions to be answered. They do note that whale recovery can be a "low regret" strategy, and I'd agree as long as it doesn't delay emissions reductions or otherwise pull resources from more proven climate solutions.</p><p></p><p></p><p><strong>BIODIVERSITY</strong>:</p><p>NatureServe's 2023 Biodiversity in Focus US report is a high level look at threatened species (imperiled or vulnerable) in the US. It's short and worth reading the whole thing. They find 34% of plant species and 40% of animal species are threatened, and 41% of the ~400 ecosystem groups in the US are at risk of "range-wide collapse" (meaning being replaced or substantially transformed). Figure 1 and 2 have breakdowns of averages for plants and animals by subgroups. For plants cacti are the worst off at 48% threatened and sedges are the least threatened at 14%. Freshwater snails are the most threatened animals (75%, and other FW groups are all more threatened than average) while birds are the least threatened (12%) and bees are about average (37%). Note that % of species that are threatened is different than looking at % of individual organisms or biomass that is threatened (all are useful metrics, Audubon's State of the Birds report looks at trends in bird population size). Figure 3 shows the most and least threatened ecosystems; unsurprisingly virtually all tropical ecosystems are threatened (they had relatively small extents originally, and are valuable for agriculture), while cliffs / rock and alpine and tundra ecosystems fare the best due to less threat of conversion to other land uses and higher rates of protection (Figure 5). They don't provide details but I would guess these are relatively short-term predictions, as climate change will threaten a lot of alpine and tundra ecosystems in the long term. Figure 4 shows how protected different species groups and ecosystems are. Almost 30% of vascular plant species are protected >50% of their range, but only 15% of vertebrate species are that protected. Finally, Figure 9b shows which states have the highest % of their area in at-risk ecosyetsms (NE, MT, and SD score the highest due to large at-risk grasslands), and Figure 11 shows priority areas for conserving imperiled species. With some exceptions (like FL) Figures 9 and 11 highlight different priority areas; Fig 11 focuses on relatively small and irreplaceable places that the most threatened species rely on, while Fig 9 focuses on more intact and lower diversity ecosystems that are at risk of being transformed (but with less potential for species extinctions). The authors conclude that the Restoring America's Wildlife Act (RAWA) guided by State Wildlife Action Plans (SWAPs) is our best bet to catalyze massive investment in conservation of the places that need it most.</p><p></p><p></p><p><strong>WILDLIFE MANAGEMENT:</strong></p><p>Jewell et al. 2023 surveyed directors and board members in charge of state wildlife agencies in the SE U.S. about future conservation challenges and how they plan to respond. They found that the respondents were focused on funding and 'agency relevance' (including changing values and fewer hunters) but less concerned about climate change (see Table 2). One quote stuck out at me, which was that they saw climate change impacts as important at time-scales beyond decades, and thus not urgent to act on (they also saw it as too political). By comparison, they saw education and outreach as critical to recruit hunters and tell the public the value of hunting and fishing. Agency directors average 5 years in office, so short-term things they can do may be more appealing. The authors call for engaging decision makers around the science of how climate change is already affecting wildlife, how that is expected to shift over time, and what actions or preparations can be taken now to help.</p><p></p><p></p><p><strong>WILDLIFE VEHICLE COLLISIONS / ROADKILL:</strong></p><p>Moore et al. 2023 is an interesting metanalysis of how vehicle collisions impact different wildlife populations around the world. Their 83 studies (of 150 populations of 69 species) are not representative / proportional of all wildlife. Most are of either even-toed ungulates (like elk and pigs) or carnivorans (like bear and big cats), roadkill studies inevitably concentrate on places where road mortality is significant, and a lot of the studies have really small samples. But they make a good case that it's a more important issue than is typically understood. Of the 58 studies that looked at roadkill as a % of all mortality over half found roadkill to be <15%, but 25 studies found 15-45% mortality from roadkill, 6 were 45-60%, and 3 were 60-80% (although they don't provide the data in a table, so I wonder if those 3 studies are weak / small N / outliers). They also found roadkill was the biggest source of mortality for 28% of populations studies, and it was in the top 3 for virtually all studies (again, likely a mix of it being an important threat AND a skewed study selection). Check out Figure 4A and 4B to see the biological orders hit hardest by roadkill (Tasmanian devils lost the most per year, opossums had the highest share of mortality from roads).</p><p></p><p><br /><strong>GENDER AND CONSERVATION (REPEAT FROM LAST MONTH):</strong><br /><a href="https://bit.ly/TNCgenderpaper" tabindex="-1" target="_blank">James et al. 2023</a> asked over 900 science & conservation staff of The Nature Conservancy about their careers and influence, and how they perceived their gender as impacting that. We found that women had less influence, experienced many barriers to their careers (including harassment, discrimination, and fear of retaliation for speaking out), and that men overestimated gender equity. Only have 5 minutes? Skip to the recommendations on page 7 (we ask orgs to: show public leadership on equity, improve transparency and accountability, diversify teams and improve career pathways for women, be flexible, include training and mentoring as part of broader change, help women connect, address sexual discrimination and harassment, and consider intersectionality). If you have 15 minutes more, read the quotes in Table 2 (p5-8) because they're really compelling and illustrative. Or if you're with the half of men and 3/4 of women in our sample who think we have more to do on gender equity (rather than that we've already "gone overboard" or that it's not an issue as some men reported), just read the whole damn paper because there's a lot of interesting detail and nuance in the results. I learned a ton while helping out on it, and I'm excited to start advocating for the recommendations. You can read it at: <a href="https://bit.ly/TNCgenderpaper" tabindex="-1" target="_blank">https://bit.ly/TNCgenderpaper</a> or a short blog <a href="https://blog.nature.org/science-brief/gender-bias-holds-women-back-in-conservation-careers/" tabindex="-1" target="_blank">at https://blog.nature.org/science-brief/gender-bias-holds-women-back-in-conservation-careers/</a> <br /><br /><br /><strong>REFERENCES:</strong></p><p>IPCC (2023). AR6 Synthesis Report. https://www.ipcc.ch/report/ar6/syr/ (accessed Mar 24, 2023).</p><p></p><p>James, R., Fisher, J. R. B., Carlos-Grotjahn, C., Boylan, M. S., Dembereldash, B., Demissie, M. Z., Diaz De Villegas, C., Gibbs, B., Konia, R., Lyons, K., Possingham, H., Robinson, C. J., Tang, T., & Butt, N. (2023). Gender bias and inequity holds women back in their conservation careers. Frontiers in Environmental Science, 10(January), 1–16. <a href="https://doi.org/10.3389/fenvs.2022.1056751" tabindex="-1" target="_blank">https://doi.org/10.3389/fenvs.2022.1056751</a> or <a href="https://bit.ly/TNCgenderpaper" tabindex="-1" target="_blank">https://bit.ly/TNCgenderpaper</a></p><p></p><p>Jewell, K., Peterson, M. N., Martin, M., Stevenson, K. T., Terando, A., & Teseneer, R. (2023). Conservation decision makers worry about relevancy and funding but not climate change. Wildlife Society Bulletin, November 2022, 1–14. https://doi.org/10.1002/wsb.1424</p><p></p><p>Moore, L. J. ., Petrovan, S. O., Bates, A. J., Hicks, H. L., Baker, P. J., Perkins, S. E., & Yarnell, R. W. (2023). Demographic effects of road mortality on mammalian populations: a systematic review. Biological Reviews, 3. https://doi.org/10.1111/brv.12942</p><p></p><p>NatureServe. (2023). Biodiversity in Focus: United States Edition. https://www.natureserve.org/sites/default/files/NatureServe_BiodiversityInFocusReport_medium.pdf<br /></p><p>Pearson, H. C., Savoca, M. S., Costa, D. P., Lomas, M. W., Molina, R., Pershing, A. J., Smith, C. R., Villaseñor-Derbez, J. C., Wing, S. R., & Roman, J. (2023). Whales in the carbon cycle: can recovery remove carbon dioxide? Trends in Ecology & Evolution, 38(3), 238–249. https://doi.org/10.1016/j.tree.2022.10.012</p><p></p><p><br />Sincerely,<br /><br />Jon<br /><br />p.s. The photo is of a dead copperhead I found on a road near Luray, VA</p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-31155220013882170102023-03-03T11:28:00.003-05:002023-03-03T11:28:41.458-05:00New paper on gender equity<p>In case you missed it in my February 2023 science summary, a new paper I co-authored on gender equity came out recently (<a href="http://bit.ly/TNCgenderpaper">James et al. 2023</a>). Here's a quick summary:</p><p><a href="http://bit.ly/TNCgenderpaper">James et al. 2023</a> asked over 900 science & conservation staff of The Nature Conservancy about their careers and influence, and how they perceived their gender as impacting that. We found that women had less influence, experienced many barriers to their careers (including harassment, discrimination, and fear of retaliation for speaking out), and that men overestimated gender equity. Only have 5 minutes? Skip to the recommendations on page 7 (you need to read the text for this list to make sense, but we ask orgs to: show public leadership on equity, improve transparency and accountability, diversify teams and improve career pathways for women, be flexible, include training and mentoring as part of broader change, help women connect, address sexual discrimination and harassment, and consider intersectionality). </p><p>If you have 15 minutes more, read the quotes in Table 2 (p5-8) because they're really compelling and illustrative. Or if you're with the half of men and 3/4 of women in our sample who think we have more to do on gender equity (rather than that we've already "gone overboard" or that it's not an issue as some men reported), just read the whole damn paper because there's a lot of interesting detail and nuance in the results. If you're a man and don't think this is an issue at your organization, it's probably worth asking a few female colleagues about their experience to see if there's anything you're missing that you could help to improve. I learned a ton while helping out on it, and I'm excited to start advocating for the recommendations. </p><p>You can read it at: <a href="https://bit.ly/TNCgenderpaper">https://bit.ly/TNCgenderpaper</a> and there's a short blog at at <a href="https://blog.nature.org/science-brief/gender-bias-holds-women-back-in-conservation-careers/">https://blog.nature.org/science-brief/gender-bias-holds-women-back-in-conservation-careers/</a></p><div><br /></div><p><br /></p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-21615222343922644492023-03-01T08:16:00.008-05:002023-03-01T08:16:00.155-05:00March 2023 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/52642828795/in/datetaken/" title="Vader trying to play while I work"><img alt="Vader trying to play while I work" height="300" src="https://live.staticflickr.com/65535/52642828795_bfae3f1185_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script>
<p>Happy March!<br /><br />A paper I'm an author on just came out (James et al. 2023) and I'm super excited about it. It looks at how science and conservation staff at The Nature Conservancy perceive gender equity in their work, and I learned a lot while working on it. Please check out the summary below, and <a data-cke-saved-href="https://bit.ly/TNCgenderpaper" href="https://bit.ly/TNCgenderpaper" target="_blank">read the whole paper</a> if you have time, or at least read this <a data-cke-saved-href="https://blog.nature.org/science-brief/gender-bias-holds-women-back-in-conservation-careers/" href="https://blog.nature.org/science-brief/gender-bias-holds-women-back-in-conservation-careers/" target="_blank">blog overview</a>.<br /><br />Also, many of you were intrigued by the use of ChatGPT last month, so I thought I'd try another AI tool to highlight what it does well and what it's limitations are. It's part of elicit.org and it's called "TL;DR papers" (for too long; didn't read). I first read about it <a data-cke-saved-href="https://www.theverge.com/2022/1/18/22889180/ai-language-summary-scientific-research-tldr-papers" href="https://www.theverge.com/2022/1/18/22889180/ai-language-summary-scientific-research-tldr-papers" target="_blank">here</a>. Elicit does many cool things, but I tested just one feature: uploading a science article and getting: 1) a 1-sentence summary of the abstract, 2) key info about the paper's design and methods, 3) critiques of the paper if it finds them, and 4) the ability to ask specific questions about the paper. I put what I did and the results below under "AI RESEARCH TOOLS." The TL;DR is that I highly recommend the "detailed abstract summary" over the default ones. I also like this <a data-cke-saved-href="https://oneusefulthing.substack.com/p/the-practical-guide-to-using-ai-to" href="https://oneusefulthing.substack.com/p/the-practical-guide-to-using-ai-to" target="_blank">guide to things to use AI for </a>(thanks to Bob Lalasz for sending it).<br /><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a data-cke-saved-href="http://eepurl.com/diB0nr" href="http://eepurl.com/diB0nr">http://b</a><a data-cke-saved-href="http://bit.ly/sciencejon" href="http://bit.ly/sciencejon" target="_blank">it.ly/sciencejon</a> (no need to email me).<br /><br /><strong>GENDER AND CONSERVATION:</strong><br /><a data-cke-saved-href="https://bit.ly/TNCgenderpaper" href="https://bit.ly/TNCgenderpaper" target="_blank">James et al. 2023</a> asked over 900 science & conservation staff of The Nature Conservancy about their careers and influence, and how they perceived their gender as impacting that. We found that women had less influence, experienced many barriers to their careers (including harassment, discrimination, and fear of retaliation for speaking out), and that men overestimated gender equity. Only have 5 minutes? Skip to the recommendations on page 7 (we ask orgs to: show public leadership on equity, improve transparency and accountability, diversify teams and improve career pathways for women, be flexible, include training and mentoring as part of broader change, help women connect, address sexual discrimination and harassment, and consider intersectionality). If you have 15 minutes more, read the quotes in Table 2 (p5-8) because they're really compelling and illustrative. Or if you're with the half of men and 3/4 of women in our sample who think we have more to do on gender equity (rather than that we've already "gone overboard" or that it's not an issue as some men reported), just read the whole damn paper because there's a lot of interesting detail and nuance in the results. I learned a ton while helping out on it, and I'm excited to start advocating for the recommendations. You can read it at: <a data-cke-saved-href="https://bit.ly/TNCgenderpaper" href="https://bit.ly/TNCgenderpaper" target="_blank">https://bit.ly/TNCgenderpaper</a> or a short blog <a data-cke-saved-href="https://blog.nature.org/science-brief/gender-bias-holds-women-back-in-conservation-careers/" href="https://blog.nature.org/science-brief/gender-bias-holds-women-back-in-conservation-careers/" target="_blank">at https://blog.nature.org/science-brief/gender-bias-holds-women-back-in-conservation-careers/</a> <br /><br /><br /><strong>AI RESEARCH TOOLS</strong>:<br />I decided to test out Elicit.org on some papers I'm an author on (to make it easy for me to judge how good or bad the info was). I picked my 5 papers that have the most citations (I'm a minor author on all but one of those), the paper which has generated the most response outside of academia (Fisher / Wood / Bradford / Kelsey 2020), and the two most recent papers I've worked on (James et al. 2023 and James et al. 2022). I used the "upload PDFs" option and uploaded all 8 PDFs at once. I pulled info from the summaries, and for each paper asked Elicit one question that I knew the paper had a good answer to. AFTER I was done I discovered Elicit has "detailed summaries" which you get by clicking in "search for paper information", so I went back and added those in with brief comments. I list direct output from Elicit in <em>italics</em>.<br /><br /><strong>Bradford et al. 2019. Soil carbon science for policy and practice</strong>. <a data-cke-saved-href="https://doi.org/10.1038/s41893-019-0431-y" href="https://doi.org/10.1038/s41893-019-0431-y" target="_blank">PAPER</a> <a data-cke-saved-href="http://sciencejon.blogspot.com/2019/11/soil-carbon-what-is-it-good-for.html" href="http://sciencejon.blogspot.com/2019/11/soil-carbon-what-is-it-good-for.html" target="_blank">BLOG</a><br /><strong>Elicit summary</strong>: "<em>Controversy about the role soils might play in climate change mitigation is undermining actions to restore soils for improved agricultural and environmental outcomes</em>."<br /><strong>Jon comments on summary</strong>: We had a 2-sentence abstract, and this is the key one. I wish it had the other key message of the paper (we know how to build soil C, and that it can help farmers) but that wasn't in our abstract so that's on us.<br /><strong>Elicit detailed summary</strong>: "<em>This paper discusses soil carbon science for policy and practice. It argues that controversy about the role soils might play in climate change mitigation is undermining actions to restore soils for improved agricultural and environmental outcomes.</em>" I really like this summary.<br /><strong>Jon comments on other findings</strong>: They classified the paper as a literature review, but it's a 'comment' so more opinion although it draws on literature. It flagged we didn't mention our funding which surprised me but it was correct! It was interesting that they said the paper had "0 citations" (it has 88) but then it did list the text from a few papers citing this paper which was cool.<br /><strong>Jon's open question</strong>: "What does building soil carbon do?" <br /><strong>Answer</strong>: "<em>Building soil carbon increases yields and reduces erosion</em>." That is pulled from the paper and is accurate.<br /><br /><strong>Fisher et al. 2018. Impact of satellite imagery spatial resolution on land use classification accuracy and modeled water quality.</strong> <a data-cke-saved-href="https://doi.org/10.1002/rse2.61" href="https://doi.org/10.1002/rse2.61" target="_blank">PAPER</a> <a data-cke-saved-href="http://bit.ly/dataresblog" href="http://bit.ly/dataresblog" target="_blank">BLOG</a><strong> </strong><br /><strong>Elicit summary</strong>: "<em>The choice of spatial resolution affected the estimated return on investment in watershed conservation for the municipal water company that finances much of this conservation.</em>"<br /><strong>Jon comments on summary</strong>: I struggled with this one, but have to agree that is the most important sentence from the abstract. I really wish they hadn't cut the 2nd half of the sentence though: ", although it is unlikely that this would have affected the company's decision to invest in the program." My TL;DR would be something like "Using free coarse imagery reduced the accuracy of our water quality modeling, but the coarse data sufficed for the purposes of the intended decision maker (a water treatment company)."<br /><strong>Elicit detailed summary</strong>: "<em>This paper compares the impact of satellite image spatial resolution on land use classification and water quality modeling. It finds that higher resolution data is more accurate but also more expensive.</em>" This is the key <em>result</em>, but the more interesting <em>implication </em>is how that wouldn't have affected the decision the research was meant to inform.<em></em><em></em><strong><br />Jon comments on other findings:</strong> The test and outcomes were good, the answer to "who were the participants" was "<em>Brazil</em>" which isn't right. It even successfully pulled the funding source from the paper's main text (this is the only article that worked for). It listed four "possible critiques" of the paper which I was excited to see and evaluate! All four papers basically echoed some of our findings so it was interesting to see they showed up as critiques (they were not): it's a ton of work to use very high resolution data (need to do lots of precise ground references, long analysis times, etc.), data resolution choice can affect your results, and one time when high resolution imagery makes sense is to classify small and heterogeneous features.<br /><strong>Jon's open question</strong>: "When is it good to use low resolution data?"<br /><strong>Answer</strong>: "<em>The paper concludes by saying that there are key criteria to assist in choosing an appropriate spatial resolution for different contexts, so it depends on the context.</em>" This is true, but Table 5 has a summary of what those criteria are, so I was bummed it didn't pull from the list of 12 answers we had to the question like: low budget, large study area, larger patches, need for frequent updates, etc.<br /><br /><strong>Fisher / Wood / Bradford / Kelsey 2020</strong> (we had equal contributions). <strong>Improving scientific impact: How to practice science that influences environmental policy and management</strong>. <a data-cke-saved-href="https://doi.org/10.1111/csp2.210" href="https://doi.org/10.1111/csp2.210" target="_blank">PAPER</a> <a data-cke-saved-href="http://sciencejon.blogspot.com/2020/09/how-scientists-can-improve-their-impact.html" href="http://sciencejon.blogspot.com/2020/09/how-scientists-can-improve-their-impact.html" target="_blank">BLOG</a><br /><strong>Elicit summary</strong>: "<em>Scientists who want to improve the impact their research has on decision-making should identify and understand the audience.</em>"<br /><strong>Jon comments on summary</strong>: Oh boy, this is a case where shorter is not better. We had 4 steps and it cut off the last 3. Here's the sentence it pulled this from "We outline a set of practical steps for scientists who want to improve the impact their research has on decision-making: (a) identify and understand the audience; (b) clarify the need for evidence; (c) gather 'just enough' evidence; and (d) share and discuss the evidence"<br /><strong>Elicit detailed summary</strong>: "<em>This paper outlines a set of practical steps for scientists who want to improve the impact their research has on decision-making. These steps include: (a) identifying and understanding the audience; (b) clarifying the need for evidence; (c) gathering "just enough" evidence; and (d) sharing and discussing the evidence.</em>" Yup - that's a good summary albeit almost a direct quote!<strong><br />Jon comments on other findings</strong>: N/A (nothing was interesting enough to discuss)<br /><strong>Jon's open question</strong>: "Why should scientists read this paper?"<br /><strong>Answer</strong>: "<em>The paper provides advice on how to make sure that 1's research has the desired impact.</em>" OK, it's weird to say "1's" for "one's", and I was hoping for noting how much research goes to waste, but this is not a bad answer.<br /><br /><strong>James et al. 2022. Gender and conservation science: Men continue to out-publish women at the world’s largest environmental conservation non-profit organization</strong>. <a data-cke-saved-href="https://doi.org/10.1111/csp2.12748" href="https://doi.org/10.1111/csp2.12748" target="_blank">PAPER</a> <a data-cke-saved-href="http://www.nature.org/en-us/newsroom/published-science-gender-gap/" href="http://www.nature.org/en-us/newsroom/published-science-gender-gap/" target="_blank">BLOG</a><br /><strong>Elicit summary</strong>: "<em>The proportion of women to men remains below gender parity at TNC.</em>"<br /><strong>Jon comments on summary</strong>: This is a great example of where truncating a sentence makes it inaccurate. While this text does appear in our abstract, it's unclear from Elicit that women are PUBLISHING less scientific articles than men, despite the fact that 45% of conservation and science staff are women.<br /><strong>Elicit detailed summary</strong>: "<em>This paper looks at the number of women publishing in conservation science at the Nature Conservancy (TNC) from 1968-2019. It finds that women are underrepresented, making up only 36% of authors, 31% of first authors, and 24% of last authors.</em>" This is a good summary and includes probably the most important high level result.<br /><strong>Jon comments on other findings</strong>: The question "what did they test" answers "<em>The duration is 1968-2019</em>" (as opposed to something like "The authors tested whether women and men at The Nature Conservancy published science articles at equal rates from 1968-2019"). The outcomes (<em># women publishing at TNC, proportion of women:men publishing at TNC, proportion of women from the Global South publishing at TNC</em>) are incomplete but true. It didn't find the 3 citations Google know about.<br /><strong>Jon's open question</strong>: "How can gender equity in science publishing be improved?"<br /><strong>Answer</strong>: "<em>The paper suggests that 'specific strategies and ongoing investments' are needed to address gender diversity among authors, especially women from outside the United States and specifically the Global South.</em>" That is frustrating, because it missed that there were seven bulleted and bolded recommendations listed under a heading called "Recommendations for building gender equity in publishing." A better (longer, but actually useful) answer would be "Gender equity in science publishing can be improved via building awareness around bias and systemic barriers, men should collaborate more with women (including in the Global South), include women performing 'invisible labor' as authors, support women to focus on publishing, support women who don't speak English as a 1st language to publish, offer dedicated publishing support for women, and manage impacts of COVID on women" (some of these don't really make sense when shortened like this, though.<br /><br /><strong>James et al. 2023. Gender bias and inequity holds women back in their conservation careers</strong>. <a data-cke-saved-href="https://doi.org/10.3389/fenvs.2022.1056751" href="https://doi.org/10.3389/fenvs.2022.1056751" target="_blank">PAPER</a><br /><strong>Elicit summary</strong>: "<em>Gender bias and inequity holds women back in their conservation careers.</em>"<br /><strong>Jon comments on summary</strong>: I mean, I'm glad it thinks the title is a good summary! But a summary of the abstract could complement the title. Maybe something like "Surveying about 900 staff of The Nature Conservancy revealed gender equity problems; the authors have recommendations to improve them"?<br /><strong>Elicit detailed summary</strong>: "<em>This paper discusses how gender bias and inequity affects women in their conservation careers.</em>" I actually think the title is still about as good as this one.<br /><strong>Jon comments on other findings</strong>: It got the participants right, and it pulled out a few details relevant to "can I trust this paper?" It couldn't find any citations b/c the paper is so new.<br /><strong>Jon's open question</strong>: "What are ways to improve gender equity?"<br /><strong>Answer</strong>: "<em>The paper proposes a series of recommendations to improve gender equity in conservation, which involve continual reviewing and adjusting policies, systems, and norms to create a culture that fully leverages the benefits of diversity</em>" Again, I wanted it to know that a question like "what are ways" means I am looking for specifics, not that "ways exist." A better answer could be "The authors recommend that organizations: show public leadership on equity, improve transparency and accountability, diversify teams and improve career pathways for women, be flexible, include training and mentoring as part of broader change, help women connect, address sexual discrimination and harassment, and consider intersectionality."<br /><br /><strong>Kroeger et al. 2014. Reforestation as a novel abatement and compliance measure for ground-level ozone</strong>. <a data-cke-saved-href="https://doi.org/10.1073/pnas.1409785111 " href="https://doi.org/10.1073/pnas.1409785111 " target="_blank">PAPER</a> <a data-cke-saved-href="http://sciencejon.blogspot.com/2014/09/reforestation-to-reduce-ozone-without.html" href="http://sciencejon.blogspot.com/2014/09/reforestation-to-reduce-ozone-without.html" target="_blank">BLOG</a><br /><strong>Elicit summary</strong>: "<em>Reforestation is a novel abatement and compliance measure for ground-level ozone.</em>"<br /><strong>Jon comments on summary</strong>: Again, this is true, but why not go beyond the title? Better to have a longer answer than to waste text by repetition: "Reforestation was predicted to abate ozone at or below the cost of conventional alternatives if land doesn't need to be purchased, and can save money if carbon offsets are generated."<br /><strong>Elicit detailed summary</strong>: For some reason Elicit declined to produce a detailed abstract summary for this one, I have no idea why!<br /><strong>Jon comments on other findings</strong>: Elicit says "no mention found of funding source" but the paper clearly states that "This analysis was done as part of the collaboration between The Nature Conservancy and Dow Chemical Company and was funded by the Dow Chemical Company Foundation." Also the one paper listed as critique this paper didn't criticize it, and just listed it as a rare case of ecosystem service valuation within industry being published in a peer-reviewed journal.<br /><b>Jon's open question</b>: "What is the national potential for reforestation to abate ozone?"<br /><strong>Answer</strong>: "Reforestation could be a viable, novel approach for abating ground level O3 pollution that complements conventional technology based controls." I was hoping for "Figure 2 maps the places in the contiguous United States where reforestation could be used to abate ozone."<br /><br /><strong>Mcdonald et al. 2009. Urban effects, distance, and protected areas in an urbanizing world</strong>. <a data-cke-saved-href="https://doi.org/10.1016/j.landurbplan.2009.06.002" href="https://doi.org/10.1016/j.landurbplan.2009.06.002" target="_blank">PAPER</a><br /><strong>Elicit summary</strong>: "<em>The median distance from a park to an urban area is already less than 50 km in many regions.</em>"<br /><strong>Jon comments on summary</strong>: That is not the key point. A better summary would be "A global review of how cities affect protected areas found that 2/3 of effects only apply within 50 km, but this proximity is common in many regions so cities are already having an impact."<br /><strong>Elicit detailed summary</strong>: "<em>This paper looks at the effects of urbanization on protected areas. It finds that thousands of protected areas are already impacted by urban areas and many more will be impacted in the future</em>." Not bad, I like my summary better but this is still good.<br /><strong>Jon comments on other findings</strong>: Again Elicit missed a partial funding statement "One of us (R.I.M.) was funded by a David H. Smith Conservation Biology Fellowship." It also couldn't access the text of any of this paper's 246 citations!<br /><strong>Jon's open question</strong>: "What were the most common threats cities posed to nature?"<br /><strong>Answer</strong>: "<em>The most common threats cities posed to nature were "housing and urban areas," "household sewage and urban waste water," "dams & water management," and "logging and wood harvesting.".</em>" Sadly this is badly wrong. It misinterpreted a few sentences this was pulled from. To be fair, the best answer is in graphic format (Fig 3) and I don't think this tool can yet read the text of images and extract insights. A better answer would be "Invasive species, housing & urban areas, fire & fire suppression, and dams & water management / use."<br /><br /><strong>Reddy et al. 2017. Advancing Conservation by Understanding and Influencing Human Behavior.</strong> <a data-cke-saved-href="https://doi.org/10.1111/conl.12252" href="https://doi.org/10.1111/conl.12252" target="_blank">PAPER </a> <br /><strong>Elicit summary</strong>: "<em>Integrating two or more behavior change approaches that target multiple, context-dependent factors may be most successful.</em>"<br /><strong>Jon comments on summary</strong>: True, but a more helpful summary would be broader: "The authors review behavior change models, providing examples and guidance on how to choose an effective one for a given context."<br /><strong>Elicit detailed summary</strong>: "<em>This paper discusses how behavioral sciences can help inform conservation policy. It provides a set of guiding questions for applying behavioral insights to conservation policy, including how to define the conservation problem as a behavior change problem, understand behavioral mechanisms, and identify and evaluate behavior change approaches.</em>" This is a good summary, no complaints.<br /><strong>Jon comments on other findings</strong>: The measured outcomes were wrong, but they got the funding source right (it was in the acknowledgments).<br /><strong>Jon's open question</strong>: "What kinds of behavior change interventions use incentives?"<br /><strong>Answer</strong>: "<em>The paper mentions that incentives are 1 of 3 behavior change approaches.</em>" This is true and it pointed me to the text listing them (awareness, incentives, and nudges). But I was looking for something like "financial or social incentives can be used to create behavior change" as per Fig 3 and a good bit of text. But to be fair I don't think we use the same terms consistently throughout.<br /><br /><br /><strong>REFERENCES:</strong></p><p>James, R., Fisher, J. R. B., Carlos-Grotjahn, C., Boylan, M. S., Dembereldash, B., Demissie, M. Z., Diaz De Villegas, C., Gibbs, B., Konia, R., Lyons, K., Possingham, H., Robinson, C. J., Tang, T., & Butt, N. (2023). Gender bias and inequity holds women back in their conservation careers. Frontiers in Environmental Science, 10(January), 1–16. <a data-cke-saved-href="https://doi.org/10.3389/fenvs.2022.1056751" href="https://doi.org/10.3389/fenvs.2022.1056751" target="_blank">https://doi.org/10.3389/fenvs.2022.1056751</a> or <a data-cke-saved-href="https://bit.ly/TNCgenderpaper" href="https://bit.ly/TNCgenderpaper" target="_blank">https://bit.ly/TNCgenderpaper</a><br /><br />Sincerely,<br /> <br />Jon<br /> <br />p.s. This is a photo of our former foster dog Vader letting me know that it was time for hand-chewing and playing, and not time for working.</p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-22663331619229583602023-02-01T08:04:00.007-05:002023-02-01T08:04:00.161-05:00February 2023 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/52628962347/in/datetaken/" title="Gyokuro green tea on vacation"><img alt="Gyokuro green tea on vacation" height="225" src="https://live.staticflickr.com/65535/52628962347_ef62e8b9e5_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script>
<p>Hi all,<br /><br />This month I have one article on metascience (problems with reproducibility may be worse than we think), two on people and nature, and one on wildlife connectivity. <br /><br />As a bonus, I wondered how my summaries would compare to automatically generated ones from Chat GPT - take a look and decide for yourself what each one is good for and what it misses! I was interested how much the length varied (I asked for a 250 word summary for each), and how much text was devoted to describing the topic without really presenting relevant results. I'll have to play around with longer summaries and see how it compares!<br /><br />I'd love to hear what others think about the ChatGPT summaries, and what your own experience playing with it has been.<br /><br /><br /><strong>METASCIENCE:</strong><br /><em><strong>Jon's summary:</strong></em><br /><strong>Breznau et al. 2022 </strong>has some scary news about science - not only is it less reproducible than we think, we can't even figure out why results vary so much. To be fair, they note that natural sciences and/or experimental research should have less variation than social science based on existing surveys (what this study looked at). But it's still concerning! Or preliminarily concerning but waiting for many more replicas, to take their message to heart. The models the 73 teams built were: 17% positive (more immigration increases support for social policies), 25% negative (more immigration reduces support for social policies), and 58% did not find a clear effect (the confidence interval included zero, although they may have had a positive or negative average effect). 61% of researchers concluded that immigration does not reduce support for social policies, 26% concluded it DOES reduce support (the text says 28.5% but it's a typo, reinforcing the core message of the paper), and 13% concluded it couldn't be tested w/ the given data. And Fig 2 shows that not only are results and conclusions all over the place, the variation isn't explained by the variables they tracked like expertise or prior beliefs. That means researcher bias is only part of the problem. I have some questions about the metanalysis itself that make me suspect they could have explained more of the variance with different methods (ironically, that is consistent with their core findings about how small method changes can drive results). But the paper reveals two problems: 1) scientists can produce different quantitative results from the same data and hypotheses, and 2) scientists' conclusions are often not well tied to their results (this paper found only ~1/3 of variation in conclusions came from how consistent the set of models each team used were). I see a lot of #2 when I peer review papers. Let's all remain humble and skeptical, and look for more replication in 2023!<br /><em><strong>ChatGPT's summary:</strong></em><strong><em></em></strong><br />The article "Observing many researchers using the same data and hypothesis reveals a hidden universe of uncertainty" published in the journal Nature Human Behavior, explores the concept of reproducibility in scientific research and its significance in understanding the reliability of scientific findings. The study conducted an experiment where multiple researchers were given access to the same data set and hypothesis, and were asked to conduct their own independent analysis and interpretation of the data. The study found that even when given the same data and hypothesis, researchers often come to different conclusions, which highlights the importance of reproducibility in scientific research. The article argues that reproducibility is crucial in determining the reliability and validity of scientific findings, and that the lack of reproducibility can lead to false conclusions and misunderstandings. The article also notes that reproducibility is not always easy to achieve, as it requires careful experimental design, sufficient sample sizes, and transparent reporting of methods and results. The article stresses on the need for scientific community to openly acknowledge and address the problem of reproducibility, as it can help in identifying the sources of uncertainty and improving the reliability of scientific research. The article concludes by emphasizing that reproducibility is a crucial aspect of the scientific process, and that it is the responsibility of the scientific community to ensure that the methods and results of scientific studies are transparent, accurate, and reproducible. The study suggests that reproducibility should be an integral part of the scientific process and should be used to identify and reduce uncertainty in scientific findings.<br /><br /><br /><strong>PEOPLE AND NATURE:</strong><br /><em><strong>Jon's summary:</strong></em><br /><strong>Chaplin-Kramer et al. 2022 </strong>is a great global summary of 14 ecosystem services I've been waiting to see for years! Their big finding is that 90% of nature's local contributions to people within each country come from a total of 30% of global land area and 24% of coastal waters (EEZs). Globally only 15% of those places are protected. The land and water needed is uneven by country (e.g., the US needs 37% of land and 15% of coastal waters), and protection varies too. See Fig 1 for the areas that provide the most benefit per unit area. The land required would be lower if optimizing globally, but at the cost of less equitable benefit distribution. The 2 global ones (carbon storage and moisture recycling) need 44% of land (optimized globally) to stay at 90% of current levels, mostly overlapping with the 30% (see Fig 3). Roughly 87% of the world population benefits from at least one of the ecosystem services, but benefits are not distributed equally (see Fig 2). The local services include: water quality (regulating nitrogen and sediment), crop pollination, livestock fodder, production of timber and fuelwood, flood regulation, fish harvest (from rivers and oceans), recreation (on land and oceans), and coastal risk reduction. If interested you can get combined GIS data from https://osf.io/r5xz7/?view_only=d611a688525f4ceb8db4ef4e7528b0e8 or one of the authors (Rachel Neugarten) is happy to send individual maps and data.<br /><em><strong>ChatGPT's summary:</strong></em><br />Mapping the planet’s critical natural assets" is an article published in the journal Nature that discusses the importance of mapping and protecting the world's natural assets, such as forests, wetlands, and coral reefs. These natural assets provide a wide range of benefits to human societies, including carbon sequestration, water regulation, and biodiversity conservation. The article emphasizes that these natural assets are under increasing threat from human activities such as deforestation, pollution, and climate change, and that urgent action is needed to protect them. The article also highlights the work of various organizations, such as the Natural Capital Project and the Intergovernmental Science-Policy Platform on Biodiversity and Ecosystem Services, that are working to map and protect these natural assets at a global scale. It also covers the importance of these natural assets for human well-being, such as providing food, medicine, and livelihoods. The article also emphasizes on the fact that these natural assets are inextricably linked with human well-being, as they provide vital ecosystem services, including air and water purification, pollination of crops, and storm protection. The article states that the current rate of loss of natural assets is alarming and calls for immediate action to be taken to protect them. The article concludes by emphasizing the need for collaboration between governments, businesses, and civil society to protect these natural assets, and to invest in sustainable land use and management practices that support the conservation and restoration of these vital resources.<br /><br /><em><strong>Jon's summary:</strong></em><br /><strong>Salvatori et al. 2023</strong> used camera traps in the Dolomite mountains of Italy to see how wildlife responded to human recreation (mostly hiking, mountain biking, and driving). They found that all 8 sampled wild species tended to favor visiting sites frequented by humans at times when humans weren't present (see Fig 5 - some of this is natural peak activity times, but more human presence resulted in a stronger temporal effect in wildlife). Bear, deer, and chamois (goat-antelopes) all avoided sites w/ more human visitation, while hares and red fox favored such sites. My main take-aways are that we should keep in mind how people will affect wildlife behavior, and that for big species we should probably look at where human trails are relative to key connectivity corridors to ensure wildlife aren't scared away from places they especially need to visit. Also - humans are looking for wildlife to interact with, while they are trying to avoid us.<br /><em><strong>ChatGPT's summary:</strong></em><br />The article "Crowded mountains: Long-term effects of human outdoor recreation on a community of wild mammals monitored with systematic camera trapping" published in the journal Biological Conservation, explores the effects of human outdoor recreation on wild mammal populations. The study conducted over a period of six years, used camera traps to monitor a community of wild mammals in the Swiss Alps. The study found that human recreational activities, such as hiking, skiing, and mountain biking, had a significant impact on wild mammal populations. The study found that wild mammal populations in areas with high levels of human recreational activity were smaller and less diverse than those in areas with low levels of human recreational activity. The study also found that the presence of human recreational activities caused wild mammal populations to shift their activity patterns, leading to increased competition for resources and reduced survival rates. The study highlights that human outdoor recreation can have a significant impact on wild mammal populations, and calls for more effective management strategies to mitigate these effects. The article emphasizes the importance of monitoring and understanding the effects of human outdoor recreation on wild mammal populations, as it can help in developing effective conservation strategies. The study suggests that creating protected areas and implementing regulations on human activities in these areas could help in reducing the negative effects of human outdoor recreation on wild mammal populations. It also suggests that educating the public about responsible outdoor recreation practices can help in reducing the impact of human activities on wild mammal populations. The study concludes by highlighting the importance of balancing human recreational activities with the protection of wild mammal populations.<br /><br /><br /><strong>WILDLIFE CONNECTIVITY<br /><em>Jon's summary:</em><br />Newmark et al. 2023 </strong>model how linking up protected areas could slow down species loss. They use "relaxation theory" to look at how long it takes for mammal species to go extinct within a given patch of habitat due to insufficiently large and resilient populations. Figure one shows how this works - the smaller the population, the less time it takes for them to go locally extinct. They focus specifically on carnivorans (like cats, canines, bears, weasels, etc.) even-toed ungulates, and lagomorphs like rabbits. Their model assumes that linking protected areas by removing all barriers will create one much larger patch of habitat which helps wildlife survive roughly four times as long. One catch: these aren't small linkages. The proposed linkages between Glacier and Yellowstone have double the area (~2.9 Mha) than the two parks being linked (~1.5 Mha), and would connect to another 2.8 Mha of wilderness in the region. So to reframe: increasing the connected habitat area by a factor of almost 5 helps species last over 4 times as long. The Mt. Rainier North Cascades uses a linkage about 2.5* the core park size. The paper makes a strong argument for the importance of well-designed connectivity work, but the big benefits they propose would also take a really big effort.<br /><em><strong>ChatGPT's summary:</strong></em><br />The article "Enhanced regional connectivity between western North American national parks will increase persistence of mammal species diversity" published in the journal Biological Conservation, examines the potential effects of enhancing regional connectivity between national parks on mammal species diversity in western North America. The study used computer simulations to model the effects of different connectivity scenarios on mammal species diversity, and found that enhanced regional connectivity between national parks would lead to an increase in the persistence of mammal species diversity. The study found that enhanced regional connectivity would allow mammal species to move more freely between national parks, which would increase genetic diversity and reduce the risk of local extinction. The study also found that enhanced regional connectivity would lead to an increase in the number of mammal species that are able to persist in the region, particularly for species that are currently at risk of extinction. The study highlights the importance of connectivity for the persistence of mammal species diversity in western North America and emphasizes the need for conservation efforts to focus on maintaining and enhancing regional connectivity. The article concludes by emphasizing the importance of preserving and enhancing regional connectivity between national parks for the protection of mammal species diversity in western North America. The study suggests that conservation efforts should focus on connecting national parks and other protected areas through corridors and other connectivity measures, to enhance the chances of mammal species survival. It also suggests that the management of these protected areas should be coordinated and integrated to improve the effectiveness of conservation efforts. The study highlights the importance of connectivity conservation as a way to ensure the long-term survival of mammal species diversity in western North America.<br /><br /><br /><strong>REFERENCES:</strong><br />Breznau, N., Rinke, E. M., Wuttke, A., Nguyen, H. H. V, Adem, M., Adriaans, J., Alvarez-Benjumea, A., Andersen, H. K., Auer, D., Azevedo, F., Bahnsen, O., Balzer, D., Bauer, G., Bauer, P. C., Baumann, M., Baute, S., Benoit, V., Bernauer, J., Berning, C., … Żółtak, T. (2022). Observing many researchers using the same data and hypothesis reveals a hidden universe of uncertainty. Proceedings of the National Academy of Sciences, 119(44), 1–8. https://doi.org/10.1073/pnas.2203150119<br /><br />Chaplin-Kramer, R., Neugarten, R. A., Sharp, R. P., Collins, P. M., Polasky, S., Hole, D., Schuster, R., Strimas-Mackey, M., Mulligan, M., Brandon, C., Diaz, S., Fluet-Chouinard, E., Gorenflo, L. J., Johnson, J. A., Kennedy, C. M., Keys, P. W., Longley-Wood, K., McIntyre, P. B., Noon, M., … Watson, R. A. (2022). Mapping the planet’s critical natural assets. Nature Ecology & Evolution. <br /><br />Newmark, W. D., Halley, J. M., Beier, P., Cushman, S. A., McNeally, P. B., & Soulé, M. E. (2023). Enhanced regional connectivity between western North American national parks will increase persistence of mammal species diversity. Scientific Reports, 13(1), 474. https://doi.org/10.1038/s41598-022-26428-z<br /><br />Salvatori, M., Oberosler, V., Rinaldi, M., Franceschini, A., Truschi, S., Pedrini, P., & Rovero, F. (2023). Crowded mountains: Long-term effects of human outdoor recreation on a community of wild mammals monitored with systematic camera trapping. Ambio. https://doi.org/10.1007/s13280-022-01825-w<br /><br /><br />Sincerely,<br /> <br />Jon<br /> <br />p.s. The photo shows my favorite kind of green tea (gyokuro) which is high in L-theanine, which in turn provides a strong umami taste and reportedly promotes a calm and alert state similar to meditation.</p><p><br /></p><p><br /></p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-68492980529364022472023-01-03T08:55:00.002-05:002024-01-25T11:57:21.066-05:00Best of 2022 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/52540734319/in/datetaken/" title="Walking Christmas tree home"><img alt="A man (Jon Fisher) carrying a large Christmas tree at an angle using a wheeled dolly. He is wearing a green Swiss Alpine hat and smiling." height="225" src="https://live.staticflickr.com/65535/52540734319_d82c239a2e_w.jpg" title="Walking home with a Christmas tree" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script><p>Happy New Year!</p><br />As usual, I'm resending summaries of my favorite 15 articles from 2022, but in case you missed any. This year I tried to group them by topic and subtopic rather than just alphabetical, but some could fit in multiple categories so apologies if it's confusing!<br /><br /><br /><strong>CONSERVATION PRIORITIES / 30x30:</strong><br /><strong><em>Biodiversity</em></strong><br /><strong>Hamilton et al. 2022 is the latest analysis from NatureServe on biodiversity in the U.S., and potential priorities for new protection.</strong> They looked at habitat for 2,216 imperiled species (G1 or G2 globally, or Threatened or Endangered nationally) across the U.S., including often overlooked species like plants and bugs. There are several interesting methodological advances here (relatively fine 1-km pixels, inclusion of overlooked species, using both range maps and habitat suitability models and showing how that changes results in Fig 4, etc.), but I think most readers will want to focus on implications for new protections and management of existing protected areas. Fig 2 shows the most important areas to protect. They use protection-weighted range-size rarity, which is a kind of rarity-weighted richness focusing on places with a) relatively high # of species that b) have relatively little habitat left nationally. Table 2 has a nice summary of how many species have the majority of their habitat managed by different groups (federal agencies, state & local, private), showing there is a lot of potential for management on existing public lands (since 43% of imperiled species have most of their habitat on public lands). It's worth reading the whole thing, but if short on time I recommend the NY Times article about this (<a data-cke-saved-href="https://urldefense.com/v3/__https:/www.nytimes.com/interactive/2022/03/03/climate/biodiversity-map.htm__;!!GF0ZRZh-yWs!3PrForRTfItKb8xc5NR6vbGepTNq306no13qu_zLYfQpqb6LJS4Vu0ay3IrM0t64413FVNGr9t0I_JM$" href="https://urldefense.com/v3/__https:/www.nytimes.com/interactive/2022/03/03/climate/biodiversity-map.htm__;!!GF0ZRZh-yWs!3PrForRTfItKb8xc5NR6vbGepTNq306no13qu_zLYfQpqb6LJS4Vu0ay3IrM0t64413FVNGr9t0I_JM$">https://www.nytimes.com/interactive/2022/03/03/climate/biodiversity-map.htm</a>) and especially the interactive maps of their data online at <a data-cke-saved-href="https://urldefense.com/v3/__https:/livingatlas.arcgis.com/en/browse/?q=mobi*d=2&q=mobi*20owner*3ANatureServe&srt=name__;IyUl!!GF0ZRZh-yWs!3PrForRTfItKb8xc5NR6vbGepTNq306no13qu_zLYfQpqb6LJS4Vu0ay3IrM0t64413FVNGr9_IblZ0$" href="https://urldefense.com/v3/__https:/livingatlas.arcgis.com/en/browse/?q=mobi*d=2&q=mobi*20owner*3ANatureServe&srt=name__;IyUl!!GF0ZRZh-yWs!3PrForRTfItKb8xc5NR6vbGepTNq306no13qu_zLYfQpqb6LJS4Vu0ay3IrM0t64413FVNGr9_IblZ0$">https://livingatlas.arcgis.com/en/browse/?q=mobi#d=2&q=mobi%20owner%3ANatureServe&srt=name</a><br /> <br /><strong>Saran et al. 2022 has a good overview of biodiversity information portals</strong>, 16 global (Table 1) and 5 country-specific (from Australia, Canada, India, and the U.S., Table 2). It's a great complement to Nicholson et al. 2021 (an overview of ecosystem indicators) by providing actual data sources and some info about what each portal includes. The paper certainly isn't "comprehensive" as the title advertises, but it's a great start and I learned about some new useful resources by reading it.<br /><br /><br /><strong><em>Climate adaptation</em></strong><br /><strong>Dreiss et al. 2022 identifies priority conservation locations within the contiguous US to support climate adaptation (via refugia and corridors).</strong> Fig 4c shows which climate refugia and corridors are unprotected (in gray) or underprotected (GAP 3 in orange). The bottom two rows in Table 3 shows that the best places for climate adaptation mostly don't overlap with the best places for biodiversity or carbon (~20-25% do). This means that focusing solely on biodiversity or carbon hotspots is likely to miss critical refugia and corridors to help ensure resilience to climate change.<br /> <br /><strong><em>Climate mitigation</em></strong>:<br /><strong>Noon et al. 2022 is a fantastic resource mapping global priority habitats for conservation to protect and/or manage to slow climate change</strong>. They focus on "irrecoverable carbon" - meaning carbon that will take 30+ years to recover after it is lost due to conversion or degradation. Fig 1 has a global map of irrecoverable carbon with a few hotspots highlighted (or use this web map which has slightly different symbology <a data-cke-saved-href="https://urldefense.com/v3/__https:/irrecoverable.resilienceatlas.org/map__;!!GF0ZRZh-yWs!17HohMYEBtcHoNdnbcEF8ksb5NRqoSf3eYaLBRGzHyVmkxJczrdwr-5mXRa1fZIL5r4PWBDEi5EqkgE$" href="https://urldefense.com/v3/__https:/irrecoverable.resilienceatlas.org/map__;!!GF0ZRZh-yWs!17HohMYEBtcHoNdnbcEF8ksb5NRqoSf3eYaLBRGzHyVmkxJczrdwr-5mXRa1fZIL5r4PWBDEi5EqkgE$">https://irrecoverable.resilienceatlas.org/map</a>). But more useful is Fig 2 which splits out the carbon by how it's threatened (by land conversion, climate change, both, or neither) to identify where protection vs. management makes sense. Note that in Fig 2 darker colors mean more carbon within each of the four risks, but they are not consistent across the four risks (to see the highest total carbon you still need Fig 1). Fig 3 highlights how uneven irrecoverable carbon in, 50% of it is in just 3% of global land area! If you work on carbon in nature, read the whole paper. Many thanks to the authors who kindly answered my questions and sent me their data so I could make my own maps!<br /> <br /><strong><em>Marine</em></strong><br /><strong>Sullivan-Stack et al. 2022 is a great summary of marine protected areas (MPAs) in the U.S.,</strong> and flags that achieving 30% U.S. ocean protection by 2030 is not on track to provide sufficient benefit to marine ecosystems. The key finding that stood out to me was the need for improving both geographic representation and efficacy / strength of protection (as well as climate resilience and equity). U.S. oceans are 26% protected overall (25% fully or highly protected), but 96% of that is in the central Pacific ocean. Excluding that region, only 2% has any protection (and only 22% of that 2% is fully or highly protected). See Table 3 for a summary of how much of each region is protected and at what level (Figure 1 has a map but it's not split by protection strength). Alaska has the lowest % protection of any kind (0.7%) while OR & WA have the weakest protection (4.2% of ocean is protected, but that's all minimal protection). Skip to section 4 for their recommendations: create more effective MPAs (via new ones and strengthening existing ones), improve representation of different marine regions & species & habitats in well-connected MPAs, improve equity & access, go beyond tracking % coverage and include impact assessments, make MPAs durable and climate resilient, coordinate state MPAs, reinstate and empower the MPA Federal Advisory Committee, strengthen & fund the NOAA MPA Center, and update the U.S. National Ocean Policy for holistic ocean planning and management.<br /><br /><br /> <br /><strong><em>Multiple goals</em></strong><br /><strong>Dreiss & Malcom 2022 is an analysis of U.S. priorities for protection under 30x30,</strong> considering hotspots of biodiversity and carbon, current protection (Fig 2), and threats. The two threats are risk of conversion (to non-habitat by 2050) and climate vulnerability (need for habitat / species to migrate elsewhere to survive, expressed in km/yr). They have two sets of hotspots, one with the top 10% of biodiversity (they calculated both imperiled species richness, and imperiled species range-size-rarity which captures how much habitat rare spp. have left), and one with the top 10% of carbon pools (not actual GHG mitigation potential, as it omits deep carbon like peat, other GHGs, and the albedo effect). Fig 3 has maps of their main results, but they're easier to see and explore in the interactive map at <a data-cke-saved-href="https://urldefense.com/v3/__https:/arcg.is/0SjGLK__;!!GF0ZRZh-yWs!m8RcNxQidO6TDSl3XMO41pbftim9hhod7XuUUzOQjp7AR5EUZgR03N6IqUJHZyeB8A$" href="https://urldefense.com/v3/__https:/arcg.is/0SjGLK__;!!GF0ZRZh-yWs!m8RcNxQidO6TDSl3XMO41pbftim9hhod7XuUUzOQjp7AR5EUZgR03N6IqUJHZyeB8A$">https://arcg.is/0SjGLK</a>. Fig 4 highlights high conversion risk (>50%) and climate vulnerability for hotspots (top 10%) of biodiversity and carbon (4a = conversion & richness, 4b = conversion & carbon, 4c = climate vuln. & richness, 4d = climate vuln. & carbon). Upgrading all existing less strict protected areas (GAP 3) would achieve ~30% protection, but that would miss 80% of biodiversity hotspots (which are on private land). Similarly, 21% of unprotected biodiversity hotspots have at least a 50% chance of being converted by 2050. The authors didn't include political, social, or economic considerations, but there are still a lot of useful data in here.<br /> <br />As conservation organizations try to work towards multiple goals, <strong>Vijay et al. 2022 asks whether we can protect places that efficiently advance multiple goals at once, or if we have to pick between places good for one goal but that perform poorly for others</strong>. We (I’m an author) looked at opportunities to advance five benefits by protecting land in the contiguous United States: vertebrate species richness, threatened vertebrate species richness, carbon storage, area protected, and recreational usage. Specifically we looked at Return On Investment (ROI) meaning the benefit score compared to the cost of the land (as a proxy for difficulty of protecting it). The results are a bit complicated: this paper focused only on unprotected habitat which is predicted to be converted by 2100, and with that framing the four environmental benefits were both highly correlated overall (r 0.89-0.99) and had a lot of the "top sites" in common (the highest scoring places for one benefit often had a top score for another benefit, 32-79% of the time). Recreation had less in common with environmental benefits (r 0.5-0.52, only 7-13% of the top sites were also a top site for another benefit). That still shows a lot of opportunity for win-wins across the nation! However, if you DON'T constrain conservation to places where land use is projected to change by 2100, win-wins are harder to find (as shown in the Supplementary Information). Species richness and area were the most compatible with a high r of 0.58 and 24% of top sites in common, and area and recreation were the least aligned, with an r of -0.65 and no top sites in common. There's a lot of interesting stuff in the paper (including comparing how three hypothetical policy scenarios score on each benefit), and I've written a slightly longer summary here: <a data-cke-saved-href="https://urldefense.com/v3/__https:/www.linkedin.com/posts/sciencejon_conservation-science-goalsetting-activity-6948122284528197632-OH0S/__;!!GF0ZRZh-yWs!zIRlfmK6P1oGPGGF5X6Pyfe2WQ9luvGgR6JWmvWNimkLeObw3FWCiWhYAhxpXeffRsOz5yMaoeVC6Dg$" href="https://urldefense.com/v3/__https:/www.linkedin.com/posts/sciencejon_conservation-science-goalsetting-activity-6948122284528197632-OH0S/__;!!GF0ZRZh-yWs!zIRlfmK6P1oGPGGF5X6Pyfe2WQ9luvGgR6JWmvWNimkLeObw3FWCiWhYAhxpXeffRsOz5yMaoeVC6Dg$">https://www.linkedin.com/posts/sciencejon_conservation-science-goalsetting-activity-6948122284528197632-OH0S/</a><br /> <br /><br /><br /><br /><strong>PROTECTED AREAS EFFECTIVENESS:</strong><br /><strong>Sze et al. 2021 compares deforestation and degradation on protected Indigenous lands</strong>, unprotected Indigenous lands, protected non-Indigenous lands, and unprotected non-Indigenous lands. Their abstract slightly misrepresents their results, which found that Indigenous lands in the tropics typically provide modest protection against deforestation and degradation, roughly similar to formal protected areas (whether Indigenous or not). The results vary by geography; in Africa unprotected Indigenous lands do even better than protected areas by most measures, but in the Americas Indigenous lands (whether protected or not) fared worse than non-Indigenous protected areas, although still better than non-Indigenous unprotected areas. In some other cases Indigenous lands seem to offer little to no improvement over unprotected non-Indigenous lands. Just comparing non-Indigenous protected areas to Indigenous protected areas, in a slight majority of cases deforestation and degradation are higher in the IPAs (but with some exceptions being similar, and degradation in Asia-Pacific being lower in IPAs); this is surprising given the other findings and makes me think that their matching process (to control for confounding variables) didn't catch everything. Another way to look at their results is that in ~90% of cases they evaluated (the 36 dark lines in Fig 2, considering both geography and data source), both protected areas and Indigenous lands (whether protected or not) experience less deforestation and degradation than unprotected non-Indigenous areas). In the remaining ~10% of cases unprotected and non-Indigenous areas have either similar levels of deforestation and degradation to protected and/or Indigenous lands, or less deforestation and degradation. Overall, the main take-away on efficacy of Indigenous lands for protection is “promising but it depends.” Their results really depend on their matching process (since without it deforestation and degradation is actually lowest in non-protected and non-Indigenous areas in a slight majority of cases). It looks like the matching should correct for confounding factors like Indigenous areas tending to be located farther from development and on lower-value lands. Most of the differences they find are pretty small. So I end up concluding that in this paper Indigenous lands are very roughly on par with protected areas, but that it’s not definitive and depends on geography.<br /><br /><br /><strong>ECOSYSTEM INDICATORS:</strong><br />You're probably familiar with the IUCN's Red List of Threatened Species - which ranks how at risk species around the world are. <strong>Comer et al. 2022 is an analysis for the Red List of ECOSYSTEMS for North America</strong> - looking at the risk of ecological collapse for 655 terrestrial ecosystems considering: current extent, how much historic extent has been lost, degradation from historic fire regime, and disruption of biotic processes (focused on invasive species and landscape fragmentation). They found 1/3 of ecosystems were threatened, and Fig 2 shows which types of ecosystems were the most threatened (like Mediterranean Scrub & Grassland, which had the highest % of extent that was threatened, and Tropical Montane Grassland & Shrubland, which had the highest % Critically Endangered). Fig 1 has a great pair of maps showing both current and historic extent of all assessed ecosystems (colored by threat level). There is also an excellent discussion of the challenges and limitations in doing an analysis like this (section 4.2). Despite these limitations, this provides a useful complement to species-focused prioritizations (like range-size rarity).<br /><br /><strong>Nicholson et al. 2021 is chock full of useful diagrams and lists for ecosystem indicators</strong>. They have a number of recommendations for setting ecosystem goals (which have milestones, targets, and indicators) for a global biodiversity framework, but which can be relevant to other efforts (like 30x30). At a high level they flag the need to track not only total ecosystem/habitat area (or extent), but also changes in ecosystem integrity (including the risk of ecosystem collapse - see Box 2 for definitions). Fig 2 is a nice visual summary of how different types of targets can collectively capture different threats and ecosystem attributes that need to be addressed for long term ecosystem health. Fig 3 is a super helpful review of many different environmental indices / metrics, and what aspects of ecosystems they include and omit. Spend some time with that one - even learning about all of the indices was very helpful for me. They close with 6 recommendations for picking indicators: we need a set of them (no single one suffices), they need to reflect goals (not actions), relevance to the goal is at least as important as data availability, we need more testing and validation of indicators, we need stronger connections between global indicators and national or local policies, and we need new indicators to provide early warning of ecosystem collapse.<br /><br /><strong>EQUITY:</strong><br /><strong><em>Fire management & Race</em></strong><br /><strong>Anderson et al. 2020 found that rich white communities who had a fire nearby tend to get additional prescribed fire (even when not needed).</strong> This is partly due to their ability to self-advocate at relevant planning meetings. It raises equity and social justice concerns about how we could instead base fire management on factors like social and/or ecological vulnerability. As context, here is a map showing how wildfire risk varies across the U.S.: <a data-cke-saved-href="https://urldefense.com/v3/__https:/blogspot.us17.list-manage.com/track/click?u=f6d3b4e334ae8760abe359341&id=d8d0494e71&e=10dbe3f36d__;!!GF0ZRZh-yWs!2iwehg-J7kFTsiP45sBc9cH2ikVNntALI56UB_p3W29wD18zD6KSnzlB-Ek6mJ8OWgKYd9wtyNqQRps$" href="https://urldefense.com/v3/__https:/blogspot.us17.list-manage.com/track/click?u=f6d3b4e334ae8760abe359341&id=d8d0494e71&e=10dbe3f36d__;!!GF0ZRZh-yWs!2iwehg-J7kFTsiP45sBc9cH2ikVNntALI56UB_p3W29wD18zD6KSnzlB-Ek6mJ8OWgKYd9wtyNqQRps$" target="_blank">https://www.nytimes.com/interactive/2022/05/16/climate/wildfire-risk-map-properties.html</a><br /><br /><br /><strong><em>Gender and Science</em></strong><br /><strong>James et al. 2022 is an analysis of how gender relates to scientific publication at The Nature Conservancy</strong> (TNC). We (I’m an author) analyzed almost 3,000 peer-reviewed scientific publications from 1968 to 2019 with at least one TNC author. Roughly 1/3 of the TNC authors and authorships (# authors * # papers) were women, even though 45% of conservation and science staff are women. Most authorships were in the U.S. - 85% overall and 90% for women. This means men (especially men in the United States) are publishing at a significantly higher rate than women. We close with several recommendations to help shrink this gap. Some are aimed at individual scientists (e.g., self-education on bias and systemic barriers, asking men to collaborate more with women as male-led papers have far fewer women co-authors than female-led papers, and asking lead authors to be more inclusive in determining whose contributions merit being listed as an author), and others are aimed at organizations (e.g., providing more resources and support for women who wish to publish, especially for women who don't speak English as a first language). I learned a ton from both the data and my co-authors on this one, and we have another 1-2 papers on the subject coming which will get into the results of a survey the lead author did to get deeper into the experience of how gender impacts not only publication but perceptions of influence and career advancement. Note that our available data listed everyone's gender as male, female, or unknown - apologies to those who we misgendered or otherwise failed to reflect their lived experience with a relatively simple binary analysis (especially as gender diverse people appear to be even more underrepresented in science publications).<br />You can read blogs about the article at <a data-cke-saved-href="https://urldefense.com/v3/__https:/www.nature.org/en-us/newsroom/published-science-gender-gap/__;!!GF0ZRZh-yWs!zIRlfmK6P1oGPGGF5X6Pyfe2WQ9luvGgR6JWmvWNimkLeObw3FWCiWhYAhxpXeffRsOz5yMaXBD5Hvc$" href="https://urldefense.com/v3/__https:/www.nature.org/en-us/newsroom/published-science-gender-gap/__;!!GF0ZRZh-yWs!zIRlfmK6P1oGPGGF5X6Pyfe2WQ9luvGgR6JWmvWNimkLeObw3FWCiWhYAhxpXeffRsOz5yMaXBD5Hvc$">https://www.nature.org/en-us/newsroom/published-science-gender-gap/</a> and <a data-cke-saved-href="https://urldefense.com/v3/__https:/blog.nature.org/science/science-brief/conservation-science-publishing-has-a-gender-problem/__;!!GF0ZRZh-yWs!zIRlfmK6P1oGPGGF5X6Pyfe2WQ9luvGgR6JWmvWNimkLeObw3FWCiWhYAhxpXeffRsOz5yMa3c5U-Kw$" href="https://urldefense.com/v3/__https:/blog.nature.org/science/science-brief/conservation-science-publishing-has-a-gender-problem/__;!!GF0ZRZh-yWs!zIRlfmK6P1oGPGGF5X6Pyfe2WQ9luvGgR6JWmvWNimkLeObw3FWCiWhYAhxpXeffRsOz5yMa3c5U-Kw$">https://blog.nature.org/science/science-brief/conservation-science-publishing-has-a-gender-problem/</a><br /><br /><br /><strong>FRESHWATER CONSERVATION</strong>:<br /><strong>Higgins et al. 2021 offers a very helpful framework for how to effectively conserve freshwater ecosystems</strong>. They argue that since freshwater species are declining faster than terrestrial species, and effective durable freshwater conservation is typically harder to get right, we need more thoughtful design of freshwater protection and management. Their framework begins with key questions (about things like what you value, key ecological attributes [KEAs] to conserve, threats to ecosystems, and protection options), which is summarized in Figure 1. Table 1 is extremely useful: it outlines 5 key ecological attributes that freshwater systems need: 1) hydrologic regime / healthy flow, 2) connectivity , 3) water quality (nutrients, sediment, toxins, etc.), 4) habitat (riparian, in-stream, other wetlands), 5) species (diversity, abundance, invasives). Table 1 also lists threats, Table 2 has conservation options, and Table 3 has helpful and relatively simple examples to get you started. Doing this work is hard! But I found this article to be a great challenge to keep thinking beyond protecting the land around freshwater ecosystems, and planning for what they need over the long-term. The lead author (Jonathan Higgins) passed away last year, you can read more about his life at <a data-cke-saved-href="https://jvhiggins.com/" href="https://jvhiggins.com/">https://jvhiggins.com/</a><br /><br /><br /><strong>FOOD / AGRICULTURE</strong>:<br /><strong>Halpern et al. 2022 is the latest paper to try and compare the global environmental footprint of almost all foods</strong> (both aquatic and terrestrial), using greenhouse gases (GHGs but excluding land use change), "blue" water consumption (from irrigation), nutrient pollution (N&P, excluding crop N fixing), and land use. Note that blue water consumption excludes rainfall, and focuses on evaporation & transpiration as opposed to "water use" (the amount pumped out) much of which returns to surface and ground water. This lets us compare the impact of different foods, look at which foods have the most total impact (and thus offer the most opportunity to improve via changes in practice or biology), and see which countries have the most environmental impact from food (India, China, the U.S., Brazil, and Pakistan - see Figs 2, 3, and especially 4). Spend some time with Fig 4, it's dense and interesting. For example, you can see that India has slightly more total impact than China, but produces substantially less food by all 3 metrics (calories, protein, and mass). Most of the data here are similar to what we've seen before, but still interesting (e.g., U.S. soy is 2.4 times more efficient than Indian soy). Reporting "cumulative" impacts can be confusing - wheat and rice have similar total impact in Fig 5, but Fig 6 shows that rice is far more inefficient per tons of protein produced). Fig 5 and 6 would be useful in looking at which crops and livestock species to focus on improved genetics or practices to have the most impact. But if you want to know "what should I eat" this paper makes it really hard to find that (Fig 6 is closest, or look at Supplementary Data 3 for country-specific "total environmental pressure" data using the food key from Table S6). So for example they find goats have a higher impact than cows, and in the US soy is the most environmentally efficient source of protein while sugar beets are the most environmentally efficient source of calories.<br /><br /><br /><br /><strong>CLIMATE MITIGATION – PEATLANDS:</strong><br /><strong>Richardson et al. 2022 estimates the potential climate mitigation benefits of rewetting drained peatlands</strong> (specifically pocosin - a bog found in the SE US dominated by trees and/or shrubs). They measured water table depth, soil characteristics, dissolved organic carbon, and emissions of CO2 & methand & nitrous oxide at 5 sites (3 drained, 1 restored, 1 natural). The drained peatlands emitted a net of 21.2 t CO2e / ha (Table 2). They conducted additional detailed measurements on the drained peatlands, and combined the data into a model to predict how water table would impact emissions. Methane and nitrous oxide were excluded since CO2 was responsible for 98% of CO2e (Fig 3). Validation found the model to be conservative and w/in 18% of measurements out of the training sample. The pocosin always emit more carbon than they absorb in fall and winter, but re-wetting peat resulted in them being a net sink in spring and summer. Rewetting from a water table 60 cm deep tp 30 cm deep cut annual net emissions by 91% (abstract says 94% but see Table 2 for the correct numbers). Rewetting from to 20 cm deep switched the pocosoins from a carbon source to a sink, sequestering 3.3 t CO2e / ha / yr. Re-wetting also reduces the risk of peat fires which would increase emissions much more. Finally, Table 3 has their estimate of how much restorable peatlands (drained peatlands currently used for agriculture or forest plantations) could be re-wetted. Note that Evans et al. 2021 earlier found that raising the water table to these levels are likely to reduce crop yields (or require a switch to different crops and cultivars), but that raising the water level to the bottom of the root zone is a clear win-win.<br /><br /><br /><br /><br /><br /><br /><strong>REFERENCES:</strong><br />Anderson, S., Plantinga, A., & Wibbenmeyer, M. (2020). Inequality in Agency Responsiveness: Evidence from Salient Wildfire Events (Issue December). <a data-cke-saved-href="https://urldefense.com/v3/__https:/www.rff.org/publications/working-papers/inequality-agency-responsiveness-evidence-salient-wildfire-events/__;!!GF0ZRZh-yWs!2iwehg-J7kFTsiP45sBc9cH2ikVNntALI56UB_p3W29wD18zD6KSnzlB-Ek6mJ8OWgKYd9wtN1oLi4k$" href="https://urldefense.com/v3/__https:/www.rff.org/publications/working-papers/inequality-agency-responsiveness-evidence-salient-wildfire-events/__;!!GF0ZRZh-yWs!2iwehg-J7kFTsiP45sBc9cH2ikVNntALI56UB_p3W29wD18zD6KSnzlB-Ek6mJ8OWgKYd9wtN1oLi4k$">https://www.rff.org/publications/working-papers/inequality-agency-responsiveness-evidence-salient-wildfire-events/</a><br /><br />Comer, P. J., Hak, J. C., & Seddon, E. (2022). Documenting at-risk status of terrestrial ecosystems in temperate and tropical North America. Conservation Science and Practice, 4(2), 1–13. <a data-cke-saved-href="https://urldefense.com/v3/__https:/doi.org/10.1111/csp2.603__;!!GF0ZRZh-yWs!zIRlfmK6P1oGPGGF5X6Pyfe2WQ9luvGgR6JWmvWNimkLeObw3FWCiWhYAhxpXeffRsOz5yMaJhmGzaY$" href="https://urldefense.com/v3/__https:/doi.org/10.1111/csp2.603__;!!GF0ZRZh-yWs!zIRlfmK6P1oGPGGF5X6Pyfe2WQ9luvGgR6JWmvWNimkLeObw3FWCiWhYAhxpXeffRsOz5yMaJhmGzaY$">https://doi.org/10.1111/csp2.603</a><br /><br />Dreiss, L. M., & Malcom, J. W. (2022). Title identifying key federal, state, and private lands strategies for achieving 30 × 30 in the United States. Conservation Letters, May 2021, 1–12. <a data-cke-saved-href="https://urldefense.com/v3/__https:/doi.org/10.1111/conl.12849__;!!GF0ZRZh-yWs!m8RcNxQidO6TDSl3XMO41pbftim9hhod7XuUUzOQjp7AR5EUZgR03N6IqUImVlKzwQ$" href="https://urldefense.com/v3/__https:/doi.org/10.1111/conl.12849__;!!GF0ZRZh-yWs!m8RcNxQidO6TDSl3XMO41pbftim9hhod7XuUUzOQjp7AR5EUZgR03N6IqUImVlKzwQ$">https://doi.org/10.1111/conl.12849</a><br /><br />Dreiss, L. M., Lacey, L. M., Weber, T. C., Delach, A., Niederman, T. E., & Malcom, J. W. (2022). Targeting current species ranges and carbon stocks fails to conserve biodiversity in a changing climate: opportunities to support climate adaptation under 30x30. Environmental Research Letters, 2(1), 0–31. <a data-cke-saved-href="https://urldefense.com/v3/__https:/doi.org/10.1088/1748-9326/ac4f8c__;!!GF0ZRZh-yWs!m8RcNxQidO6TDSl3XMO41pbftim9hhod7XuUUzOQjp7AR5EUZgR03N6IqUIBC2II-A$" href="https://urldefense.com/v3/__https:/doi.org/10.1088/1748-9326/ac4f8c__;!!GF0ZRZh-yWs!m8RcNxQidO6TDSl3XMO41pbftim9hhod7XuUUzOQjp7AR5EUZgR03N6IqUIBC2II-A$">https://doi.org/10.1088/1748-9326/ac4f8c</a><br /><br />Halpern, B. S., Frazier, M., Verstaen, J., Rayner, P., Clawson, G., Blanchard, J. L., Cottrell, R. S., Froehlich, H. E., Gephart, J. A., Jacobsen, N. S., Kuempel, C. D., McIntyre, P. B., Metian, M., Moran, D., Nash, K. L., Többen, J., & Williams, D. R. (2022). The environmental footprint of global food production. Nature Sustainability. <a data-cke-saved-href="https://urldefense.com/v3/__https:/doi.org/10.1038/s41893-022-00965-x__;!!GF0ZRZh-yWs!wxIaQumrR_6Wa8Q8V6KfNLNgCIugjrNmGNRU3_7Az4W86EGeWHWxGX8RuKiFYhkC742_DGIlGaIL0Fw$" href="https://urldefense.com/v3/__https:/doi.org/10.1038/s41893-022-00965-x__;!!GF0ZRZh-yWs!wxIaQumrR_6Wa8Q8V6KfNLNgCIugjrNmGNRU3_7Az4W86EGeWHWxGX8RuKiFYhkC742_DGIlGaIL0Fw$">https://doi.org/10.1038/s41893-022-00965-x</a><br /><br />Hamilton, H., Smyth, R. L., Young, B. E., Howard, T. G., Tracey, C., Breyer, S., Cameron, D. R., Chazal, A., Conley, A. K., Frye, C., & Schloss, C. (2022). Increasing taxonomic diversity and spatial resolution clarifies opportunities for protecting US imperiled species. Ecological Applications, 32(3), 1–19. <a data-cke-saved-href="https://urldefense.com/v3/__https:/doi.org/10.1002/eap.2534__;!!GF0ZRZh-yWs!3PrForRTfItKb8xc5NR6vbGepTNq306no13qu_zLYfQpqb6LJS4Vu0ay3IrM0t64413FVNGr0BTOusQ$" href="https://urldefense.com/v3/__https:/doi.org/10.1002/eap.2534__;!!GF0ZRZh-yWs!3PrForRTfItKb8xc5NR6vbGepTNq306no13qu_zLYfQpqb6LJS4Vu0ay3IrM0t64413FVNGr0BTOusQ$">https://doi.org/10.1002/eap.2534</a><br /><br />Higgins, J., Zablocki, J., Newsock, A., Krolopp, A., Tabas, P., & Salama, M. (2021). Durable Freshwater Protection: A Framework for Establishing and Maintaining Long-Term Protection for Freshwater Ecosystems and the Values They Sustain. Sustainability, 13(4), 1950. <a data-cke-saved-href="https://urldefense.com/v3/__https:/doi.org/10.3390/su13041950__;!!GF0ZRZh-yWs!zIRlfmK6P1oGPGGF5X6Pyfe2WQ9luvGgR6JWmvWNimkLeObw3FWCiWhYAhxpXeffRsOz5yMaeHR0R2g$" href="https://urldefense.com/v3/__https:/doi.org/10.3390/su13041950__;!!GF0ZRZh-yWs!zIRlfmK6P1oGPGGF5X6Pyfe2WQ9luvGgR6JWmvWNimkLeObw3FWCiWhYAhxpXeffRsOz5yMaeHR0R2g$">https://doi.org/10.3390/su13041950</a><br /><br />James, R., Ariunbaatar, J., Bresnahan, M., Carlos‐Grotjahn, C., Fisher, J. R. B., Gibbs, B., Hausheer, J. E., Nakozoete, C., Nomura, S., Possingham, H., & Lyons, K. (2022). Gender and conservation science: Men continue to out‐publish women at the world’s largest environmental conservation non‐profit organization. Conservation Science and Practice, January, 1–9. <a data-cke-saved-href="https://urldefense.com/v3/__https:/doi.org/10.1111/csp2.12748__;!!GF0ZRZh-yWs!zIRlfmK6P1oGPGGF5X6Pyfe2WQ9luvGgR6JWmvWNimkLeObw3FWCiWhYAhxpXeffRsOz5yMafyh58L8$" href="https://urldefense.com/v3/__https:/doi.org/10.1111/csp2.12748__;!!GF0ZRZh-yWs!zIRlfmK6P1oGPGGF5X6Pyfe2WQ9luvGgR6JWmvWNimkLeObw3FWCiWhYAhxpXeffRsOz5yMafyh58L8$">https://doi.org/10.1111/csp2.12748</a><br /><br />Nicholson, E., Watermeyer, K. E., Rowland, J. A., Sato, C. F., Stevenson, S. L., Andrade, A., Brooks, T. M., Burgess, N. D., Cheng, S.-T., Grantham, H. S., Hill, S. L., Keith, D. A., Maron, M., Metzke, D., Murray, N. J., Nelson, C. R., Obura, D., Plumptre, A., Skowno, A. L., & Watson, J. E. M. (2021). Scientific foundations for an ecosystem goal, milestones and indicators for the post-2020 global biodiversity framework. Nature Ecology & Evolution, 5(10), 1338–1349. <a data-cke-saved-href="https://urldefense.com/v3/__https:/doi.org/10.1038/s41559-021-01538-5__;!!GF0ZRZh-yWs!2HkOuxAp2t2Nf25DV03-sLxFgbal2PpCWJ-Ykk42cYgbvWkTncTGDWAfvC8ZmQ6bRZYa8PuEowAPNyE$" href="https://urldefense.com/v3/__https:/doi.org/10.1038/s41559-021-01538-5__;!!GF0ZRZh-yWs!2HkOuxAp2t2Nf25DV03-sLxFgbal2PpCWJ-Ykk42cYgbvWkTncTGDWAfvC8ZmQ6bRZYa8PuEowAPNyE$">https://doi.org/10.1038/s41559-021-01538-5</a><br /><br />Noon, M. L., Goldstein, A., Ledezma, J. C., Roehrdanz, P. R., Cook-Patton, S. C., Spawn-Lee, S. A., Wright, T. M., Gonzalez-Roglich, M., Hole, D. G., Rockström, J., & Turner, W. R. (2022). Mapping the irrecoverable carbon in Earth’s ecosystems. Nature Sustainability, 5(1), 37–46. <a data-cke-saved-href="https://urldefense.com/v3/__https:/doi.org/10.1038/s41893-021-00803-6__;!!GF0ZRZh-yWs!17HohMYEBtcHoNdnbcEF8ksb5NRqoSf3eYaLBRGzHyVmkxJczrdwr-5mXRa1fZIL5r4PWBDElUA-TMs$" href="https://urldefense.com/v3/__https:/doi.org/10.1038/s41893-021-00803-6__;!!GF0ZRZh-yWs!17HohMYEBtcHoNdnbcEF8ksb5NRqoSf3eYaLBRGzHyVmkxJczrdwr-5mXRa1fZIL5r4PWBDElUA-TMs$">https://doi.org/10.1038/s41893-021-00803-6</a><br /><br />Richardson, C. J., Flanagan, N. E., Wang, H., & Ho, M. (2022). Annual carbon sequestration and loss rates under altered hydrology and fire regimes in southeastern USA pocosin peatlands. Global Change Biology, July, 1–15. <a data-cke-saved-href="https://urldefense.com/v3/__https:/doi.org/10.1111/gcb.16366__;!!GF0ZRZh-yWs!wxIaQumrR_6Wa8Q8V6KfNLNgCIugjrNmGNRU3_7Az4W86EGeWHWxGX8RuKiFYhkC742_DGIlu6e1pJE$" href="https://urldefense.com/v3/__https:/doi.org/10.1111/gcb.16366__;!!GF0ZRZh-yWs!wxIaQumrR_6Wa8Q8V6KfNLNgCIugjrNmGNRU3_7Az4W86EGeWHWxGX8RuKiFYhkC742_DGIlu6e1pJE$">https://doi.org/10.1111/gcb.16366</a><br /><br />Saran, S., Chaudhary, S. K., Singh, P., Tiwari, A., & Kumar, V. (2022). A comprehensive review on biodiversity information portals. Biodiversity and Conservation, 0123456789. <a data-cke-saved-href="https://urldefense.com/v3/__https:/doi.org/10.1007/s10531-022-02420-x__;!!GF0ZRZh-yWs!2iwehg-J7kFTsiP45sBc9cH2ikVNntALI56UB_p3W29wD18zD6KSnzlB-Ek6mJ8OWgKYd9wt03hNJzA$" href="https://urldefense.com/v3/__https:/doi.org/10.1007/s10531-022-02420-x__;!!GF0ZRZh-yWs!2iwehg-J7kFTsiP45sBc9cH2ikVNntALI56UB_p3W29wD18zD6KSnzlB-Ek6mJ8OWgKYd9wt03hNJzA$">https://doi.org/10.1007/s10531-022-02420-x</a><br /> <br />Sullivan-Stack, J., Aburto-Oropeza, O., Brooks, C. M., Cabral, R. B., Caselle, J. E., Chan, F., Duffy, J. E., Dunn, D. C., Friedlander, A. M., Fulton-Bennett, H. K., Gaines, S. D., Gerber, L. R., Hines, E., Leslie, H. M., Lester, S. E., MacCarthy, J. M. C., Maxwell, S. M., Mayorga, J., McCauley, D. J., … Grorud-Colvert, K. (2022). A Scientific Synthesis of Marine Protected Areas in the United States: Status and Recommendations. Frontiers in Marine Science, 9(May), 1–23. <a data-cke-saved-href="https://urldefense.com/v3/__https:/doi.org/10.3389/fmars.2022.849927__;!!GF0ZRZh-yWs!2HkOuxAp2t2Nf25DV03-sLxFgbal2PpCWJ-Ykk42cYgbvWkTncTGDWAfvC8ZmQ6bRZYa8PuEJtalyb0$" href="https://urldefense.com/v3/__https:/doi.org/10.3389/fmars.2022.849927__;!!GF0ZRZh-yWs!2HkOuxAp2t2Nf25DV03-sLxFgbal2PpCWJ-Ykk42cYgbvWkTncTGDWAfvC8ZmQ6bRZYa8PuEJtalyb0$">https://doi.org/10.3389/fmars.2022.849927</a><br /><br />Sze, J. S., Carrasco, L. R., Childs, D., & Edwards, D. P. (2021). Reduced deforestation and degradation in Indigenous Lands pan-tropically. Nature Sustainability, 2. <a data-cke-saved-href="https://urldefense.com/v3/__https:/doi.org/10.1038/s41893-021-00815-2__;!!GF0ZRZh-yWs!nTPcRNQwJozRBO9CVlaudJ5VnBgNsTMnHCUhv-CY-bOqlyl5sxCDUV74qfd2XAV5uQ$" href="https://urldefense.com/v3/__https:/doi.org/10.1038/s41893-021-00815-2__;!!GF0ZRZh-yWs!nTPcRNQwJozRBO9CVlaudJ5VnBgNsTMnHCUhv-CY-bOqlyl5sxCDUV74qfd2XAV5uQ$">https://doi.org/10.1038/s41893-021-00815-2</a><br /> <br />Vijay, V., Fisher, J. R. B., & Armsworth, P. R. (2022). Co‐benefits for terrestrial biodiversity and ecosystem services available from contrasting land protection policies in the contiguous United States. Conservation Letters, February, 1–9. <a data-cke-saved-href="https://urldefense.com/v3/__https:/doi.org/10.1111/conl.12907__;!!GF0ZRZh-yWs!zIRlfmK6P1oGPGGF5X6Pyfe2WQ9luvGgR6JWmvWNimkLeObw3FWCiWhYAhxpXeffRsOz5yMaENggghQ$" href="https://urldefense.com/v3/__https:/doi.org/10.1111/conl.12907__;!!GF0ZRZh-yWs!zIRlfmK6P1oGPGGF5X6Pyfe2WQ9luvGgR6JWmvWNimkLeObw3FWCiWhYAhxpXeffRsOz5yMaENggghQ$">https://doi.org/10.1111/conl.12907</a><br /><br /><br /><div>Happy New Year,<br /><br />Jon<br /><br />p.s. We continue to find creative ways to get by without a car. The photo shows that this year we wheeled our Christmas tree home using a dolly from a lot a bit over a mile away.</div>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-24725694468286633932022-12-01T08:11:00.007-05:002022-12-01T08:11:00.163-05:00December 2022 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/52485469847/in/dateposted/" title="Victoria sunrise"><img alt="Victoria sunrise" height="185" src="https://live.staticflickr.com/65535/52485469847_ee1ff362a2_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script><p>Happy December,</p><p><br />In the spirit of the paper on gratitude below: thank you all for helping me to be a better scientist and a better person. Almost every month I get a note or two from someone who found the summary useful, or who had a question / critique / idea that I learned from. That engagement has helped me push myself to keep doing these, which in terms helps me be a bit more well-read. So thank you!<br /><br />Also, while they're too long to summarize briefly like I do with papers, I want to recommend the books "Think Again" by Adam Grant and "Noise" by Daniel Kahneman, Olivier Sibony, and Cass R. Sunstein. Taken together, they've given me a lot of ideas about how to get better at reevaluating my beliefs, improving how I review evidence and draw conclusions, and generate estimates. Email me if you want some notes I took on my favorite parts of each!<br /><br /><br /><strong>GRATITUDE:</strong><br />As a follow-up to the Thanksgiving holiday, I wanted to share a review of a paper on gratitude by Wood et al. 2010. It's a broad review of research on the topic and fairly wonky, but I found a few things useful. I liked how table 1 lists complementary aspects of gratitude: noticing how grateful you are overall, feeling gratitude towards others, focusing on what you have (vs. what you lack), feelings of awe, expressing gratitude (internally and to others), being present, living to the fullest b/c of awareness that life is short, and feeling lucky when thinking about how things could be worse. They cover quite a lot of research on gratitude and how being more grateful is associated w/ better quality of life (although there's some question how much gratitude causes well-being vs. is just correlated). The biggest boost to feeling good came from writing a letter thanking someone and reading it to them in person, but keeping a daily diary of three things you're grateful for seems to be easier to keep up and helps you feel better for longer.<br /><br /><br /><strong>CLIMATE CHANGE</strong><br />Reich et al. 2022 is an interesting experiment of how boreal forests might respond to 1.6C or 3.1C warming, using open-air heaters in an actual forest (as well as simulating reduced rainfall by covering some of the soil) to see how they respond. Conifers experienced slower growth (Fig 2) and higher mortality (Fig 1). How much varied by species, with balsam fir showing the worst impact. Compared to current conditions, warming or limited rain each reduced balsam fir growth by ~1/3, while the combination reduced growth by ~2/3. Seedling survival went down by ~40% at 1.6C, ~72% at 3.1C, and ~84% at 3.1C plus less rain. But others like jack pine had much smaller effects, and some trees like maples had similar survival rates and more growth under warming (even with less rain). So they predict that conifers will become less dominant, over the long term being replaced by deciduous trees but in the short term more likely replaced by invasive woody shrubs (since the deciduous trees aren't common enough to spread fast). There is an article about this written for general audiences at <a data-cke-saved-href="https://phys.org/news/2022-08-modest-climate-northernmost-forests.html" href="https://phys.org/news/2022-08-modest-climate-northernmost-forests.html" target="_blank">https://phys.org/news/2022-08-modest-climate-northernmost-forests.html</a><br /><br /><br /><strong>SUSTAINABLE RANCHING:</strong><br />Santos et al. 2017 is an interesting paper on using fuzzy logic to assess beef sustainability in the Pantanal. As background - fuzzy logic doesn't mean 'sloppy reasoning' - it's actually a real thing which more or less centers on non-binary logic models. For example, old thermostats are non-fuzzy (they turn on when cold and turn off when warm enough), but newer ones are often fuzzy (adjusting fan speed, turning auxiliary heat on or off, etc. depending on performance). In this case, they take a ton of practical indicators, map each onto a 4 point scale, and combine them into a single "overall sustainability index" (see Figure 1). Check out Appendix I for the list of how well each indicator matched expert judgments.<br /><br /><br /><strong>OTTERS:</strong><br />Valladares et al. 2022 used drones to figure out what kind of habitat giant otters in Peru most preferred. They found giant otters preferred oxbow lakes with the largest water surface area, the least floating vegetation (more open water), and more dense forest canopy cover along the banks of the lakes.</p><p><br /><br /><strong>REFERENCES:</strong><br />Reich, P. B., Bermudez, R., Montgomery, R. A., Rich, R. L., Rice, K. E., Hobbie, S. E., & Stefanski, A. (2022). Even modest climate change may lead to major transitions in boreal forests. Nature, 608(7923), 540–545. https://doi.org/10.1038/s41586-022-05076-3<br /><br />Santos, S. A., de Lima, H. P., Massruhá, S. M. F. S., de Abreu, U. G. P., Tomás, W. M., Salis, S. M., Cardoso, E. L., de Oliveira, M. D., Soares, M. T. S., dos Santos, A., de Oliveira, L. O. F., Calheiros, D. F., Crispim, S. M. A., Soriano, B. M. A., Amâncio, C. O. G., Nunes, A. P., & Pellegrin, L. A. (2017). A fuzzy logic-based tool to assess beef cattle ranching sustainability in complex environmental systems. Journal of Environmental Management, 198, 95–106. https://doi.org/10.1016/j.jenvman.2017.04.076<br /><br />Valladares, N. A., Pardo, A. A., Chiaverini, L., Groenendijk, J., Harrington, L. A., Macdonald, D. W., Swaisgood, R. R., & Barocas, A. (2022). High‐resolution drone imagery reveals drivers of fine‐scale giant otter habitat selection in the land‐water interface. Conservation Science and Practice, December 2021, 1–14. https://doi.org/10.1111/csp2.12786<br /><br />Wood, A. M., Froh, J. J., & Geraghty, A. W. A. (2010). Gratitude and well-being: A review and theoretical integration. Clinical Psychology Review, 30(7), 890–905. https://doi.org/10.1016/j.cpr.2010.03.005<br /><br /><br />Sincerely,<br /> <br />Jon</p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-11433220504529350422022-11-01T08:07:00.001-04:002022-11-01T08:07:00.156-04:00November 2022 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/52467380186/in/datetaken/" title="Jack o' lantern w bloodshot eyes"><img alt="Jack o' lantern w bloodshot eyes" height="225" src="https://live.staticflickr.com/65535/52467380186_d16e722d49_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script>
<div>Greetings,</div><div><p>Happy belated Halloween!<br /><br />This month I have four articles on different facets of climate change (drought, ecological adaptation, and mitigation through peatlands), plus one big new global paper on the environmental impact of food.<br /><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a data-cke-saved-href="http://eepurl.com/diB0nr" href="http://eepurl.com/diB0nr">http://b</a><a data-cke-saved-href="http://bit.ly/sciencejon" href="http://bit.ly/sciencejon" target="_blank">it.ly/sciencejon</a></p><p><br /><br /><strong>FOOD / AGRICULTURE</strong>:<br />Halpern et al. 2022 is the latest paper to try and compare the global environmental footprint of almost all foods (both aquatic and terrestrial), using greenhouse gases (GHGs but excluding land use change), "blue" water consumption (from irrigation), nutrient pollution (N&P, excluding crop N fixing), and land use. Note that blue water consumption excludes rainfall, and focuses on evaporation & transpiration as opposed to "water use" (the amount pumped out) much of which returns to surface and ground water. This lets us compare the impact of different foods, look at which foods have the most total impact (and thus offer the most opportunity to improve via changes in practice or biology), and see which countries have the most environmental impact from food (India, China, the U.S., Brazil, and Pakistan - see Figs 2, 3, and especially 4). Spend some time with Fig 4, it's dense and interesting. For example, you can see that India has slightly more total impact than China, but produces substantially less food by all 3 metrics (calories, protein, and mass). Most of the data here are similar to what we've seen before, but still interesting (e.g., U.S. soy is 2.4 times more efficient than Indian soy). Reporting "cumulative" impacts can be confusing - wheat and rice have similar total impact in Fig 5, but Fig 6 shows that rice is far more inefficient per tons of protein produced). Fig 5 and 6 would be useful in looking at which crops and livestock species to focus on improved genetics or practices to have the most impact. But if you want to know "what should I eat" this paper makes it really hard to find that (Fig 6 is closest, or look at Supplementary Data 3 for country-specific "total environmental pressure" data using the food key from Table S6). So for example they find goats have a higher impact than cows, and in the US soy is the most environmentally efficient source of protein while sugar beets are the most environmentally efficient source of calories.<br /><br /><br /><strong>CLIMATE CHANGE & DROUGHT:</strong><br />Cook et al. 2015 estimates the likelihood of summer droughts (June through August) in the American Central Plains and Southwest between 2050 and 2100. Their findings are striking, even under the RCP 4.5 climate scenario (which they put in the supplement, focusing instead on the much less likely RCP 8.5 scenario). They predict the following chances of a decadal (11 year) or multidecadal (35 year) drought: decadal ~94% Central Plains and ~97% Southwest, multidecadal ~73% Central Plains and ~80% for Southwest (see Fig S13 on the past page of the supplement). That's pretty scary, and they further note this is drier than even the historically dry period from the years 1100-1300. However, this is a lot more pessimistic than the IPCC (as the authors acknowledge), and I'm not qualified to go deep enough in the methods to weigh in as to how likely this is. But as we have already seen out West, droughts lasting multiple years have very different implications both for communities and agriculture. Tree crops will be increasingly untenable as the risk of multi-year droughts increase, and farmers may have to switch to very different crops to make it through these dry periods.<br /><br /><br /><strong>CLIMATE ADAPTATION (ECOLOGICAL):</strong><br />Moore and Schindler 2022 is an opinion piece arguing that more diverse strategies are needed to help prepare ecosystems for climate change. They argue that conservation needs to adapt to shifting ecosystems and unpredictable futures by maintaining complexity, especially by promoting enhanced gene flow and facilitating the ability of habitat to shift to new places as climate changes. Given uncertainty in climate changes and ecosystem response, they argue that refugia may not be as robust as promoting climate corridors and habitat heterogeneity. Local conservation work to address current stresses and future threats is another important aspect of improving resilience: by working on known threats we can make ecosystems more able to withstand the unknown. Finally, as ecosystems and populations shift, resource management needs to adapt to these new realities rather than sticking to long-term plans.<br /><br /><br /><strong>PEATLANDS - CLIMATE MITIGATION:</strong><br />Richardson et al. 2022 estimates the potential climate mitigation benefits of rewetting drained peatlands (specifically pocosin - a bog found in the SE US dominated by trees and/or shrubs). They measured water table depth, soil characteristics, dissolved organic carbon, and emissions of CO2 & methand & nitrous oxide at 5 sites (3 drained, 1 restored, 1 natural). The drained peatlands emitted a net of 21.2 t CO2e / ha (Table 2). They conducted additional detailed measurements on the drained peatlands, and combined the data into a model to predict how water table would impact emissions. Methane and nitrous oxide were excluded since CO2 was responsible for 98% of CO2e (Fig 3). Validation found the model to be conservative and w/in 18% of measurements out of the training sample. The pocosin always emit more carbon than they absorb in fall and winter, but re-wetting peat resulted in them being a net sink in spring and summer. Rewetting from a water table 60 cm deep tp 30 cm deep cut annual net emissions by 91% (abstract says 94% but see Table 2 for the correct numbers). Rewetting from to 20 cm deep switched the pocosoins from a carbon source to a sink, sequestering 3.3 t CO2e / ha / yr. Re-wetting also reduces the risk of peat fires which would increase emissions much more. Finally, Table 3 has their estimate of how much restorable peatlands (drained peatlands currently used for agriculture or forest plantations) could be re-wetted. Note that Evans et al. 2021 earlier found that raising the water table to these levels are likely to reduce crop yields (or require a switch to different crops and cultivars), but that raising the water level to the bottom of the root zone is a clear win-win.<br /><br />Goldstein et al. 2020 looks at peat fires in Indonesia and what causes them, especially the sub-surface fires which cause the most air pollution and can burn for a long time. Their answer: it's complicated. They essentially find three requirements for sub-surface fires: 1) drainage lowers the water table and dries out the peat, 2) fire is ignited (for one of many reasons), and 3) enough fuel is present (like tree logs) that the fire burns long enough to reach deeper layers (dry weather also has a big influence). Much of the widespread use of fire does NOT result in these deep fires, b/c either the site isn't dry enough or it burns often enough there is insufficient fuel on the surface. The authors try hard not to blame anyone for these fires, but do argue that major drainage projects are likely a dominant factor.<br /><br /><br /><strong>REFERENCES:</strong></p><p>Cook, B. I., Ault, T. R., & Smerdon, J. E. (2015). Unprecedented 21st century drought risk in the American Southwest and Central Plains. Science Advances, 1(1), 1–8. https://doi.org/10.1126/sciadv.1400082<br /><br />Goldstein, J. E., Graham, L., Ansori, S., Vetrita, Y., Thomas, A., Applegate, G., Vayda, A. P., Saharjo, B. H., & Cochrane, M. A. (2020). Beyond slash‐and‐burn: The roles of human activities, altered hydrology and fuels in peat fires in Central Kalimantan, Indonesia. Singapore Journal of Tropical Geography, 41(2), 190–208. https://doi.org/10.1111/sjtg.12319<br /><br />Halpern, B. S., Frazier, M., Verstaen, J., Rayner, P., Clawson, G., Blanchard, J. L., Cottrell, R. S., Froehlich, H. E., Gephart, J. A., Jacobsen, N. S., Kuempel, C. D., McIntyre, P. B., Metian, M., Moran, D., Nash, K. L., Többen, J., & Williams, D. R. (2022). The environmental footprint of global food production. Nature Sustainability. https://doi.org/10.1038/s41893-022-00965-x<br /><br />Moore, J. W., & Schindler, D. E. (2022). Getting ahead of climate change for ecological adaptation and resilience. Science, 376(6600), 1421–1426. https://doi.org/10.1126/science.abo3608<br /><br />Richardson, C. J., Flanagan, N. E., Wang, H., & Ho, M. (2022). Annual carbon sequestration and loss rates under altered hydrology and fire regimes in southeastern USA pocosin peatlands. Global Change Biology, July, 1–15. https://doi.org/10.1111/gcb.16366<br /><br /><br />Sincerely,<br /> <br />Jon<br /> <a data-cke-saved-href="http://sciencejon.blogspot.com/" href="http://sciencejon.blogspot.com/" target="_blank"><br /></a>p.s. the photo was my attempt to make a Jack o 'lantern w/ bloodshot eyes</p></div>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-56124165371290212952022-10-03T08:45:00.001-04:002022-10-03T08:45:00.145-04:00October 2022 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/52281749492/" title="Calli & Jon on porch"><img alt="Calli & Jon on porch" height="300" src="https://live.staticflickr.com/65535/52281749492_e929f0800f_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script>
<p>Greetings,</p><p><br />This month I am summarizing two science articles on climate change and one on conservation prioritization<br /><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a data-cke-saved-href="http://eepurl.com/diB0nr" href="http://eepurl.com/diB0nr">http://b</a><a data-cke-saved-href="http://bit.ly/sciencejon" href="http://bit.ly/sciencejon" target="_blank">it.ly/sciencejon</a> (no need to email me).<br /><br /><strong>CONSERVATION PRIORITIES:<br /></strong>Belote et al. 2021 is a great analysis comparing how different ways of identifying spatial conservation priorities overlap and conflict in the lower 48 states of the US. They focus on 4 groups of vertebrates (mammals, birds, amphibians, and reptiles), and 4 methods of prioritizing: species richness, rarity-weighted richness, and two Zonation approaches that favor complementarity / representation (ABF favors species richness, CAZ favors rarity). Fig 1 has the most interesting maps if you want to compare the approaches, and Fig 3 highlights the places with the most agreement across models that they are in the top 30% of options. It's a great way to see how your values and methods can affect your results (but also that some places are pretty agreed on priorities). Two things to contrast with the NatureServe "map of biodiversity importacet" - that analysis includes plants and some invertebrates (this does not), and NatureServe focuses on imperiled species while this is threat-blind. One last note on the zonation approaches - these work best as a complete set; if you pick and choose among them they don't perform nearly as well, and it's rare that science recommendations are ever taken up entirely. But conversely a focus solely on richness or rarity misses lower diversity ecosystems and wide-ranging species.<br /><br /><br /><strong>CLIMATE CHANGE</strong>:<br />Temmink et al. 2022 is an overview of carbon storage and cycling in wetlands. They note peatlands and coastal wetlands have much higher carbon stock density than forests or oceans, and also sequester more carbon each year (see the figure in the Review Summary for a nice overview, or Fig 1 for more detail). They also focus on how healthy wetlands have feedbacks that support high productivity and/or low decomposition (see Fig 2), but that people are disrupting those feedbacks. They show how much of these ecosystems have been lost already, and how fast they are disappearing (Table 1) and estimate this amoutns to 500 million metric tons of C lost each year. They closeby arguing that keeping wetlands intact is key for climate mitigation. One caution though - they focus only on carbon, and some wetlands emit quite a lot of methane and nitrous oxide. Those are much stronger GHGs than CO2, so the net climate benefit of wetlands is smaller than you'd think from looking at carbon alone.<br /><br />Law et al. 2018 is an analysis of how more trees in Oregon (planting, cutting less often, and halting cutting) can lead to more climate mitigation benefits and cobenefits of water availability (maybe, stay tuned on that). From 2011-2015, OR forests already on net sequestered the equivalent of 72% of OR's total GHGs (Fig 2), and they think that could be boosted by 56% with a series of programs. See Figure 3 for this potential, but note the bars each represent a single decade (and the lower figure is annual change within that decade), with cumulative results from 2015-2100 showing up as numbers in italics OVER the bars. This confused me pretty thoroughly, and it looks to me from the Figure like annual "net ecosystem carbon balance" (~=net carbon sequestered) by 2100 would increase by ~1.2 Tg C / yr, not the 2-3 they say in the text. They also find that using harvest residues for bioenergy would lead to a net increase in emissions (even assuming 1/2 of residues replace coal or natural gas). One thing that struck me as very odd: they propose afforesting grass crops which are irrigated but not used for food or forage, and claiming water will be freed up by doing so. But I can't figure why someone would irrigate grass if it wasn't used for food (or things like lawns or golf courses which forests wouldn't be compatible with)- maybe it's literally fields to produce grass seed sold for lawns? <br />Peter Ellis from TNC had this take which I found helpful (that this shouldn't be taken as having national implications): "The study is constrained to the Pacific Northwest (PNW). If you care about carbon, you can never really beat leaving a PNW forest alone. No attempts to sell the idea of mitigation through bioenergy or wood product storage are going to beat carbon storage in forests in a region where: <br />• Trees are largest in the world<br />• They take forever to decompose, so coarse woody debris storage is really important.<br />Their proposal for Oregon’s forest actually makes a lot of sense to me: 'reforestation, afforestation, lengthened harvest cycles on private lands, and restricting harvest on public lands increased net ecosystem carbon balance by 56% by 2100'"<br /><br /><strong>REFERENCES:</strong></p><p>Belote, R. T., Barnett, K., Dietz, M. S., Burkle, L., Jenkins, C. N., Dreiss, L., Aycrigg, J. L., & Aplet, G. H. (2021). Options for prioritizing sites for biodiversity conservation with implications for “30 by 30.” Biological Conservation, 264, 109378. https://doi.org/10.1016/j.biocon.2021.109378<br /><br />Law, B. E., Hudiburg, T. W., Berner, L. T., Kent, J. J., Buotte, P. C., & Harmon, M. E. (2018). Land use strategies to mitigate climate change in carbon dense temperate forests. Proceedings of the National Academy of Sciences, 115(14), 3663–3668. https://doi.org/10.1073/pnas.1720064115<br /><br />Temmink, R. J. M., Lamers, L. P. M., Angelini, C., Bouma, T. J., Fritz, C., van de Koppel, J., Lexmond, R., Rietkerk, M., Silliman, B. R., Joosten, H., & van der Heide, T. (2022). Recovering wetland biogeomorphic feedbacks to restore the world’s biotic carbon hotspots. Science, 376(6593). https://doi.org/10.1126/science.abn1479<br /><br /><br />Sincerely,<br /> <br />Jon<br /> <br />p.s. This is a recent picture of me and my neighbor's adorable snaggletoothed dog Calli on our porch (we were dogsitting).</p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-37041230845038744722022-09-01T08:30:00.013-04:002022-09-01T08:43:11.323-04:00September 2022 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/52246457670/in/datetaken/" title="Goldfinches on cutleaf coneflowers"><img alt="Goldfinches on cutleaf coneflowers" height="300" src="https://live.staticflickr.com/65535/52246457670_ef3a64e034_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script>
<p>Hi,</p><p><br />First I wanted to say how sorry I was to hear that one of the lead authors I highlighted last month (Jonathan Higgins) has since passed away. Higs was a force of nature and he will be missed by many. I'm very glad that my last email exchange with him was about how useful his paper was and the impact I thought it would have, which made him very happy.<br /><br />This month I am summarizing three articles on climate change, one on tropical forest recovery, and one on conservation and human well-being. If you know someone who wants to sign up to receive these summaries, they can do so at <a data-cke-saved-href="http://eepurl.com/diB0nr" href="http://eepurl.com/diB0nr">http://b</a><a data-cke-saved-href="http://bit.ly/sciencejon" href="http://bit.ly/sciencejon" target="_blank">it.ly/sciencejon</a> (no need to email me).</p><p><br /><br /><strong>CLIMATE CHANGE:</strong><br />Gopalakrishna et al. 2022 highlights the need for local studies of climate mitigation potential. They found that if you avoid conflict w/ ag lands, forest restoration potential is lower in India than global estimates (and they suspect the same would be true in other tropical countries with lots of ag lands). They found 1.6 million ha of lands that could be restored; the plurality was degraded forest followed by scrub. If those lands were restored, they estimate it could provide 61.3 Mt (million tons) of carbon sequestration. They also roughly estimate 14.7 million ha of ag lands could incorporate agroforestry practices for up to another 98 Mt of carbon over 30 years. So the key take-aways here are a) we can't rely on global estimates for in-country work and b) if we can find ways to add trees to lands producing food w/o impacting food production (which is sometimes possible) there is a lot of opportunity there.<br /><br />Noon et al. 2022 is a fantastic resource mapping global priority habitats for conservation to protect and/or manage to slow climate change. They focus on "irrecoverable carbon" - meaning carbon that will take 30+ years to recover after it is lost due to conversion or degradation. Fig 1 has a global map of irrecoverable carbon with a few hotspots highlighted (or use this web map which has slightly different symbology https://irrecoverable.resilienceatlas.org/map). But more useful is Fig 2 which splits out the carbon by how it's threatened (by land conversion, climate change, both, or neither) to identify where protection vs. management makes sense. Note that in Fig 2 darker colors mean more carbon within each of the four risks, but they are not consistent across the four risks (to see the highest total carbon you still need Fig 1). Fig 3 highlights how uneven irrecoverable carbon in, 50% of it is in just 3% of global land area! If you work on carbon in nature, read the whole paper. Many thanks to the authors who kindly answered my questions and sent me their data so I could make my own maps!<br /><br />Reed 2021 tackles the thorny issue of how montane meadowns in California (wet grasslands in mountains) mitigate or worsen climate change. They found that a) these ecosystems store a lot of carbon, b) on net they can be either a big carbon source (10/13 sites) or a big carbon sink (3/13 sites) c) the sites that were a source had similar plant species to sink sites, but typically had groundwater closer to the surface, more root biomass, and less bare ground, d) methane emissions were consistently low, and e) they're not sure what caused most meadows to become net carbon sources (the high carbon stock indicate they all used to be sinks) but think it depends mostly on how much water and dissolved carbon flows into the meadows from uplands and thus upland forest loss is a likely culprit. The discussion is interesting - they hypothesize that hydrologic restoration in the meadow and upland forest management could slow carbon losses but think it's a safer bet to try and maintain sites that are currently net carbon sinks.<br /><br /><br /><strong>FOREST RESILIENCE / RECOVERY</strong>:<br />Poorter et al. 2021 look at how long it took for tropical forests (in Central & South America plus West Africa) to recover after deforestation, finding them pretty resilient. They found recovery to 90% of old growth values took 1-9 yrs for soil, plant function took 3-27 yrs, forest structure took 27-119 (tree size variation 27, max tree size 49, biomass 119), species diversity took 37-59, and species composition took 120 years. They thus argue secondary (regrowing) forests are still ecologically important and deserve conservation (protection, restoration, and management). Note that most of their sites had low to mid intensity land use after deforestation like swidden agriculture, so soil degradation was relatively minor. It's short and worth the read, but as is common w/ papers in Science I found the figures hard to decipher but useful once you put in the time. Fig 1B shows roughly how quickly different attributes recover over time (soil is brown, plant function is purple, structure is green, and diversity is turquoise); Fig 2 is similar but breaks out sub-indicators and is more precise; and Fig 3D is my favorite (how long it takes each attribute to return to 90% of old growth values). Here are the abbreviations since they are not defined in a single place! <br />AGB=aboveground biomass<br />BD=soil bulk density<br />C=soil carbon<br />DMAX=maximum tree diameter<br />N=soil nitrogen<br />NF=proportional basal area of nitrogen-fixing species<br />SC=species composition (how similar abundance of each species is to old growth)<br />SD=Simpson diversity (~diversity of common species)<br />SH=structural heterogeneity (variation in tree size)<br />SR=species richness (number of species present)<br />SLA=community-weighted mean specific leaf area<br />WD=community-weighted mean wood density<br /><br /><br /><strong>NATURE & PEOPLE:</strong><br />Huynh et al. 2022 is a global literature review of 300 peer-reviewed papers on the many intangible ways nature impacts people (what they call "cultural ecosystem services" or CESs). So it leaves out physical effects like providing food, clean water, reducing storms, etc. (which are well studied) and focuses on things like recreation, spiritual fulfillment, aesthetics, etc. If you enjoy taxonomies / classifications you will like this paper, and if not, you will find it a slog, since the heart of it is a framework to classify many ways people and nature interact (see Table 1 and Figure 2). But it's worth at least reading through Table 1 and pondering a bit. Ssome like how nature can help people bond ('Cohesive') were new to me but rang true; others felt like splitting hairs (e.g., splitting spiritual experiences into 'Intuitive' and 'Transcendentive'). Beyond the framework, they found 86% of over 1,000 observations positively impacted people (more studies looked at this and there is likely bias in the lit - it's not necessarily that nature is inherently overwhelmingly beneficial). Their expert judgment is that the biggest benefits come from mental and physical health, particularly from recreation (including tourism) and aesthetic values (the size of boxes in Fig 3 shows how many studies they had for each of 227 'pathways').The biggest negative impacts came from concern about safety ('Apprehensive'), or the loss of ecosystem services when nature is damaged or lost ('Destructive' - although it seems odd to me to mix that in with actual harms from nature itself), with only a few 'Irritative' (annoyance or disgust, e.g., from wildlife noise or excrement). In the end the paper gave me 'Cognitive' benefits but was not very 'Satisfactive.' The Washington Post has an overview of the paper here: https://www.washingtonpost.com/climate-solutions/2022/08/05/nature-study-impact-hiking-outdoors/<br /><br /><br /><strong>REFERENCES:</strong></p><p>Gopalakrishna, T., Lomax, G., Aguirre‐Gutiérrez, J., Bauman, D., Roy, P. S., Joshi, P. K., & Malhi, Y. (2022). Existing land uses constrain climate change mitigation potential of forest restoration in India. Conservation Letters, December 2021, 1–11. https://doi.org/10.1111/conl.12867</p><p>Huynh, L. T. M., Gasparatos, A., Su, J., Dam Lam, R., Grant, E. I., & Fukushi, K. (2022). Linking the nonmaterial dimensions of human-nature relations and human well-being through cultural ecosystem services. Science Advances, 8(31), 1–22. https://doi.org/10.1126/sciadv.abn8042<br /><br />Noon, M. L., Goldstein, A., Ledezma, J. C., Roehrdanz, P. R., Cook-Patton, S. C., Spawn-Lee, S. A., Wright, T. M., Gonzalez-Roglich, M., Hole, D. G., Rockström, J., & Turner, W. R. (2022). Mapping the irrecoverable carbon in Earth’s ecosystems. Nature Sustainability, 5(1), 37–46. https://doi.org/10.1038/s41893-021-00803-6<br /><br />Poorter, L., Craven, D., Jakovac, C. C., van der Sande, M. T., Amissah, L., Bongers, F., Chazdon, R. L., Farrior, C. E., Kambach, S., Meave, J. A., Muñoz, R., Norden, N., Rüger, N., van Breugel, M., Almeyda Zambrano, A. M., Amani, B., Andrade, J. L., Brancalion, P. H. S., Broadbent, E. N., … Hérault, B. (2021). Multidimensional tropical forest recovery. Science, 374(6573), 1370–1376. https://doi.org/10.1126/science.abh3629<br /><br />Reed, C. C., Merrill, A. G., Drew, W. M., Christman, B., Hutchinson, R. A., Keszey, L., Odell, M., Swanson, S., Verburg, P. S. J., Wilcox, J., Hart, S. C., & Sullivan, B. W. (2021). Montane Meadows: A Soil Carbon Sink or Source? Ecosystems, 24(5), 1125–1141. https://doi.org/10.1007/s10021-020-00572-x<br /><br /> </p><p>p.s. the photo shows a goldfinch amidst my cutleaf coneflowers, watching me watch him (these flowers are only ~5 ft from a living room window)</p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-71992971182326499952022-08-01T08:30:00.001-04:002022-08-01T08:30:00.156-04:00August 2022 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/52191131284/" title="Bubble in garden"><img alt="Bubble in garden" height="300" src="https://live.staticflickr.com/65535/52191131284_9bec4fcf92_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script>
<p>Hi,<br /><br />After publishing no peer-reviewed science in 2021, two papers I'm a co-author on were published this month!<br /><br /> The first (<a data-cke-saved-href="https://www.linkedin.com/pulse/can-conservation-advance-several-goals-once-do-we-have-jon-fisher/" href="https://www.linkedin.com/pulse/can-conservation-advance-several-goals-once-do-we-have-jon-fisher/" target="_blank">Vijay et al. 2022</a>) looks at how different conservation goals for people and nature tend to align and conflict: identifying both win-wins and trade-offs to inform conservation priorities. The second (<a data-cke-saved-href="https://www.nature.org/en-us/newsroom/published-science-gender-gap/" href="https://www.nature.org/en-us/newsroom/published-science-gender-gap/" target="_blank">James et al. 2022</a>) is an analysis of scientific publications by staff at The Nature Conservancy split by gender, along with recommendations to improve the ability of women (especially from the Global South) to publish research. Let me know if you have questions about either after reading the summaries below!<br /><br />I've also got an interesting article on the IUCN Red List of threatened ecosystems, and a great framework to think through freshwater conservation needs and approaches.<br /><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a data-cke-saved-href="http://eepurl.com/diB0nr" href="http://eepurl.com/diB0nr">http://b</a><a data-cke-saved-href="http://bit.ly/sciencejon" href="http://bit.ly/sciencejon" target="_blank">it.ly/sciencejon</a> (no need to email me).<br /><br /><strong>GENDER AND SCIENCE:</strong><br />James et al. 2022 analyzed almost 3,000 peer-reviewed scientific publications with at least one author from The Nature Conservancy (TNC) by gender of the author(s) - all that we could find from 1968 to 2019. Roughly 1/3 of the TNC authors and authorships (# authors * # papers) were women, even though 45% of conservation and science staff are women. Most authorships were in the U.S. - 85% overall and 90% for women. This means men (especially men in the United States) are publishing at a significantly higher rate than women. We close with several recommendations to help shrink this gap. Some are aimed at individual scientists (e.g., self-education on bias and systemic barriers, asking men to collaborate more with women as male-led papers have far fewer women co-authors than female-led papers, and asking lead authors to be more inclusive in determining whose contributions merit being listed as an author), and others are aimed at organizations (e.g., providing more resources and support for women who wish to publish, especially for women who don't speak English as a first language). I learned a ton from both the data and my co-authors on this one, and we have another 1-2 papers on the subject coming which will get into the results of a survey the lead author did to get deeper into the experience of how gender impacts not only publication but perceptions of influence and career advancement. Note that our available data listed everyone's gender as male, female, or unknown - apologies to those who we misgendered or otherwise failed to reflect their lived experience with a relatively simple binary analysis (especially as gender diverse people appear to be even more underrepresented in science publications).<br />You can read blogs about the article at <a href="https://www.nature.org/en-us/newsroom/published-science-gender-gap/">https://www.nature.org/en-us/newsroom/published-science-gender-gap/</a> and <a href="https://blog.nature.org/science/science-brief/conservation-science-publishing-has-a-gender-problem/">https://blog.nature.org/science/science-brief/conservation-science-publishing-has-a-gender-problem/</a><br /><br /><br /><strong>CONSERVATION PRIORITIZATION</strong>:<br />As conservation organizations try to work towards multiple goals, Vijay et al. 2022 asks whether we can protect places that efficiently advance multiple goals at once, or if we have to pick between places good for one goal but that perform poorly for others. We looked at opportunities to advance five benefits by protecting land in the contiguous United States: vertebrate species richness, threatened vertebrate species richness, carbon storage, area protected, and recreational usage. Specifically we looked at Return On Investment (ROI) meaning the benefit score compared to the cost of the land (as a proxy for difficulty of protecting it). The results are a bit complicated: this paper focused only on unprotected habitat which is predicted to be converted by 2100, and with that framing the four environmental benefits were both highly correlated overall (r 0.89-0.99) and had a lot of the "top sites" in common (the highest scoring places for one benefit often had a top score for another benefit, 32-79% of the time). Recreation had less in common with environmental benefits (r 0.5-0.52, only 7-13% of the top sites were also a top site for another benefit). That still shows a lot of opportunity for win-wins across the nation! However, if you DON'T constrain conservation to places where land use is projected to change by 2100, win-wins are harder to find (as shown in the Supplementary Information). Species richness and area were the most compatible with a high r of 0.58 and 24% of top sites in common, and area and recreation were the least aligned, with an r of -0.65 and no top sites in common. There's a lot of interesting stuff in the paper (including comparing how three hypothetical policy scenarios score on each benefit), and I've written a slightly longer summary here: <a href="https://www.linkedin.com/posts/sciencejon_conservation-science-goalsetting-activity-6948122284528197632-OH0S/">https://www.linkedin.com/posts/sciencejon_conservation-science-goalsetting-activity-6948122284528197632-OH0S/</a><br /><br />You're probably familiar with the IUCN's Red List of Threatened Species - which ranks how at risk species around the world are. Comer et al. 2022 is an analysis for the Red List of ECOSYSTEMS for North America - looking at the risk of ecological collapse for 655 terrestrial ecosystems considering: current extent, how much historic extent has been lost, degradation from historic fire regime, and disruption of biotic processes (focused on invasive species and landscape fragmentation). They found 1/3 of ecosystems were threatened, and Fig 2 shows which types of ecosystems were the most threatened (like Mediterranean Scrub & Grassland, which had the highest % of extent that was threatened, and Tropical Montane Grassland & Shrubland, which had the highest % Critically Endangered). Fig 1 has a great pair of maps showing both current and historic extent of all assessed ecosystems (colored by threat level). There is also an excellent discussion of the challenges and limitations in doing an analysis like this (section 4.2). Despite these limitations, this provides a useful complement to species-focused prioritizations (like range-size rarity).<br /><br /><br /><strong>FRESHWATER CONSERVATION</strong>:<br />Higgins et al. 2021 (from a team of scientists and lawyers) argues that since freshwater species are declining faster than terrestrial species, and effective durable freshwater conservation is typically harder to get right, we need more thoughtful design of freshwater protection and management. They offer a framework to do that, beginning with key questions (about things like what you value, key ecological attributes [KEAs] to conserve, threats to ecosystems, and protection options), which is summarized in Figure 1. Table 1 is extremely useful: it outlines 5 key ecological attributes that freshwater systems need: 1) hydrologic regime / healthy flow, 2) connectivity , 3) water quality (nutrients, sediment, toxins, etc.), 4) habitat (riparian, in-stream, other wetlands), 5) species (diversity, abundance, invasives). Table 1 also lists threats, Table 2 has conservation options, and Table 3 has helpful and relatively simple examples to get you started. Doing this work is hard! But I found this article to be a great challenge to keep thinking beyond protecting the land around freshwater ecosystems, and planning for what they need over the long-term.<br /><br /><strong>REFERENCES:</strong></p><p>Comer, P. J., Hak, J. C., & Seddon, E. (2022). Documenting at-risk status of terrestrial ecosystems in temperate and tropical North America. Conservation Science and Practice, 4(2), 1–13. <a href="https://doi.org/10.1111/csp2.603">https://doi.org/10.1111/csp2.603</a><br /><br />Higgins, J., Zablocki, J., Newsock, A., Krolopp, A., Tabas, P., & Salama, M. (2021). Durable Freshwater Protection: A Framework for Establishing and Maintaining Long-Term Protection for Freshwater Ecosystems and the Values They Sustain. Sustainability, 13(4), 1950. <a href="https://doi.org/10.3390/su13041950">https://doi.org/10.3390/su13041950</a><br /><br />James, R., Ariunbaatar, J., Bresnahan, M., Carlos‐Grotjahn, C., Fisher, J. R. B., Gibbs, B., Hausheer, J. E., Nakozoete, C., Nomura, S., Possingham, H., & Lyons, K. (2022). Gender and conservation science: Men continue to out‐publish women at the world’s largest environmental conservation non‐profit organization. Conservation Science and Practice, January, 1–9. <a href="https://doi.org/10.1111/csp2.12748">https://doi.org/10.1111/csp2.12748</a><br /><br />Vijay, V., Fisher, J. R. B., & Armsworth, P. R. (2022). Co‐benefits for terrestrial biodiversity and ecosystem services available from contrasting land protection policies in the contiguous United States. Conservation Letters, February, 1–9. <a href="https://doi.org/10.1111/conl.12907">https://doi.org/10.1111/conl.12907</a><br /><br /><br />Sincerely,<br /> <br />Jon<br /> <br />p.s. This large bubble is over my 'butterfly garden' which is currently full of <a data-cke-saved-href="https://www.flickr.com/photos/jaundicedferret/52229897826" href="https://www.flickr.com/photos/jaundicedferret/52229897826" target="_blank">flowers</a> and <a data-cke-saved-href="https://www.flickr.com/photos/jaundicedferret/52229897776/in/datetaken/" href="https://www.flickr.com/photos/jaundicedferret/52229897776/in/datetaken/" target="_blank">pollinators</a>!</p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-35030839373435023442022-07-06T14:20:00.000-04:002022-07-06T14:20:00.895-04:00Two new papers: how gender impacts science publishing & conservation prioritization<p>After having 0 papers published in 2021, I was on author on two papers published last week (both open access - click the author name to go to the paper)! Here's a quick summary of each:</p><p><b><a href="https://onlinelibrary.wiley.com/doi/10.1111/csp2.12748">James et al. 2022</a></b> analyzed almost 3,000 peer-reviewed scientific publications with at least one author from The Nature Conservancy (TNC) by<b> gender</b> of the author(s) - all that we could find from 1968 to 2019. Roughly 1/3 of the TNC authors and authorships (# authors * # papers) were women, even though 45% of conservation and science staff are women. Most authorships were in the U.S. - 85% overall and 90% for women. This means men (especially men in the United States) are publishing at a significantly higher rate than women. We close with several recommendations to help shrink this gap. Some are aimed at individual scientists (e.g., self-education on bias and systemic barriers, asking men to collaborate more with women as male-led papers have far fewer women co-authors than female-led papers, and asking lead authors to be more inclusive in determining whose contributions merit being listed as an author), and others are aimed at organizations (e.g., providing more resources and support for women who wish to publish, especially for women who don't speak English as a first language). </p><p>I learned a ton from both the data and my co-authors on this one, and we have another 1-2 papers on the subject coming which will get into the results of a survey the lead author did to get deeper into the experience of how gender impacts not only publication but perceptions of influence and career advancement. Note that our available data listed everyone's gender as male, female, or unknown - apologies to those who we misgendered or otherwise failed to reflect their lived experience with a relatively simple binary analysis (especially as gender diverse people appear to be even more underrepresented in science publications).</p><p>You can read blogs about the article at <a href="https://www.nature.org/en-us/newsroom/published-science-gender-gap">https://www.nature.org/en-us/newsroom/published-science-gender-gap</a>/ and <a href="https://blog.nature.org/science/science-brief/conservation-science-publishing-has-a-gender-problem/">https://blog.nature.org/science/science-brief/conservation-science-publishing-has-a-gender-problem/</a> or the full paper is at <a href="https://onlinelibrary.wiley.com/doi/10.1111/csp2.12748">https://onlinelibrary.wiley.com/doi/10.1111/csp2.12748</a></p><p><br /></p><p>As conservation organizations try to work towards multiple goals, <b><a href="https://onlinelibrary.wiley.com/doi/10.1111/conl.12907">Vijay et al. 2022</a></b> asks whether we can protect places that efficiently advance multiple goals at once (<b>win-wins</b>), or if we have to pick between places good for one goal but that perform poorly for others (<b>trade-offs</b>). We looked at opportunities to advance five benefits by protecting land in the contiguous United States: vertebrate species richness, threatened vertebrate species richness, carbon storage, area protected, and recreational usage. Specifically we looked at Return On Investment (ROI) meaning the benefit score compared to the cost of the land (as a proxy for difficulty of protecting it). </p><p>The results are a bit complicated: this paper focused only on unprotected habitat which is predicted to be converted by 2100, and with that framing the four environmental benefits were both highly correlated overall (r 0.89-0.99) and had a lot of the "top sites" in common (the highest scoring places for one benefit often had a top score for another benefit, 32-79% of the time). Recreation had less in common with environmental benefits (r 0.5-0.52, only 7-13% of the top sites were also a top site for another benefit). That still shows a lot of opportunity for win-wins across the nation! However, if you DON'T constrain conservation to places where land use is projected to change by 2100, win-wins are harder to find (as shown in the Supplementary Information). Species richness and area were the most compatible with a high r of 0.58 and 24% of top sites in common, and area and recreation were the least aligned, with an r of -0.65 and no top sites in common. </p><p>There's a lot of interesting stuff in the paper (including comparing how three hypothetical policy scenarios score on each benefit), and I've written a slightly longer summary here: <a href="https://www.linkedin.com/posts/sciencejon_conservation-science-goalsetting-activity-6948122284528197632-OH0S/">https://www.linkedin.com/posts/sciencejon_conservation-science-goalsetting-activity-6948122284528197632-OH0S/</a> or the full paper is at <a href="https://onlinelibrary.wiley.com/doi/10.1111/conl.12907">https://onlinelibrary.wiley.com/doi/10.1111/conl.12907</a></p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-80597744298449238962022-07-01T08:00:00.001-04:002022-07-01T08:00:00.167-04:00July 2022 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/52137138129/" title="Bromeliad fly (Copestylum) on spiderwort (Tradescantia)"><img alt="Bromeliad fly (Copestylum) on spiderwort (Tradescantia)" height="365" src="https://live.staticflickr.com/65535/52137138129_ca2c83d732_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script>
<p>Hello,</p><p><br />This month is another grab bag: one paper on equity in fire management, two on biodiversity data, one asking how much conservation has helped species, and one pretty bad one on how ag practices impact nutrients.<br /><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a data-cke-saved-href="http://eepurl.com/diB0nr" href="http://eepurl.com/diB0nr">http://b</a><a data-cke-saved-href="http://bit.ly/sciencejon" href="http://bit.ly/sciencejon" target="_blank">it.ly/sciencejon</a> (no need to email me).<br /><br /><strong>FIRE MANAGEMENT:</strong><br />Anderson et al. 2020 found that rich white communities who had a fire nearby tend to get additional prescribed fire (even when not needed). This is partly due to their ability to self-advocate at relevant planning meetings. It raises equity and social justice concerns about how we could instead base fire management on factors like social and/or ecological vulnerability. As context, here is a map showing how wildfire risk varies across the U.S.: <a data-cke-saved-href="https://www.nytimes.com/interactive/2022/05/16/climate/wildfire-risk-map-properties.html" href="https://www.nytimes.com/interactive/2022/05/16/climate/wildfire-risk-map-properties.html" target="_blank">https://www.nytimes.com/interactive/2022/05/16/climate/wildfire-risk-map-properties.html</a><br /><br /><br /><strong>BIODIVERSITY DATA</strong>:<br />Saran et al. 2022 has a good overview of biodiversity information portals, 16 global (Table 1) and 5 country-specific (from Australia, Canada, India, and the U.S., Table 2). It's a great complement to Nicholson et al. 2021 (an overview of ecosystem indicators) by providing actual data sources and some info about what each portal includes. The paper certainly isn't "comprehensive" as the title advertises, but it's a great start and I learned about some new useful resources by reading it.<br /><br />Before threatened species can get protection, they need to be assessed to document how vulnerable they are. But there is a substantial backlog of species waiting to be assessed. Levin et al. 2022 offers a fairly simple (but ultimately unsuccessful) way to re-prioritize unassessed species for the IUCN red list to allow a better chance of assessing the ones that are in trouble so they can get protection. They use a rapid estimate of "extent of occurrence" (the species' range and spatial distribution of threats) as a proxy for vulnerability. At first it's exciting to see that it was 92% accurate at identifying which species were of the Least Concern (showing potential to flag species not worth assessing). But two questions are more relevant (and Fig 1 has the answers): what % of vulnerable species does it correctly recommend assessing (40%) and what % of recommendations for assessment are for species that are actually vulnerable (23%). The discussion has interesting notes on some of the aspects that confused the model (like 5 ash app threatened by Emerald Ash Borer and the American Chestnut threatened by blight) - widespread spp. hit hard by invasives are challenging to accurately assess using simple approaches like this. Hopefully the next iteration of the tool will be more successful, if they could substantially reduce false negatives for vulnerable species it could provide assessment priorities directly, or if they could substantially reduce false positives for vulnerable species it could help by indicating species that likely shouldn't be assessed.<br /><br /><br /><strong>CONSERVATION IMPACT</strong>:<br />Jellesmark et al. 2022 is a global (see Fig 1 map) preprint looking at how conservation has impacted targeted vertebrate species (by comparing pairs of populations targeted for conservation with those in the same country that did not receive conservation attention). I honestly don't know enough about the underlying data source (Living Planet Database) to speak to the reliability of their results (I'll wait for peer review for that, there is at least one very important typo where they use "invertebrate" when they clearly mean "vertebrate"). They found that population size of assessed vertebrates dropped 24% over 46 years, but estimate that without conservation it would have dropped 32% (and this likely underestimates the impact of conservation). They split out conservation actions into 7 groups (land/water protection, land/water mgmt, species mgmt, education/awareness, law/policy, livelihoods/incentives, and external capacity building), and capacity building followed by the first three showed the strongest results (Fig 5).<br /><br /><br /><strong>SUSTAINABLE AGRICULTURE</strong>:<br />Montgomery et al. 2022 asks how nutrients from ‘regenerative’ farms (that use no-till, crop rotations, and cover crops) differ from other farms, but I wouldn't recommend it. This paper is pretty weak methodologically, results were inappropriately highlighted and over-interpreted, and the results I initially planned to write about didn’t hold up when I looked at raw data. Some key caveats: it is a very small sample size, 4/5 authors have financial interests the paper furthers, only one author appears to be a scientist (a geomorphologist), and the methods are thin and read like they may have gone looking for pairs of farms that would support the desired narrative (plus they used a very rough method to measure organic matter). At first I thought the most interesting / meaningful results are for cabbage: 10 assessed nutrients were substantially higher on regenerative farms, compared to 4 that were the same, 4 that were substantially lower, and 3 not assessed. But when you dive in, that 70% difference in vitamin E is from 0.004 to 0.007 mg/100g (essentially nil). Ditto with wheat results, 50% more calcium than “almost none” is still almost none. The animal results are hard to interpret because they don’t provide enough detail on differences between ‘regenerative’ vs. ‘conventional’ (although findings that grass-finished beef have more nutrient content have been reported in other lit, in alignment w/ results here). Some results look more meaningful (20% more vitamin C in cabbage is worthwhile) but there is such variation in the soil organic matter and soil health across the farms it’s really hard to know what is significant and what is accidental. One last note - 'regenerative' here almost certainly means 'genetically modified’ for most crops, since it’s hard to do no-till without them.<br /><br /><br /><strong>REFERENCES:</strong></p><p>Anderson, S., Plantinga, A., & Wibbenmeyer, M. (2020). Inequality in Agency Responsiveness: Evidence from Salient Wildfire Events (Issue December). https://www.rff.org/publications/working-papers/inequality-agency-responsiveness-evidence-salient-wildfire-events/<br /><br />Jellesmark, S., Blackburn, T. M., Dove, S., Geldmann, J., Visconti, P., Gregory, R. D., McRae, L., & Hoffmann, M. (2022). Assessing the global impact of targeted conservation actions on species abundance. BioRxiv, 2022.01.14.476374. https://doi.org/10.1101/2022.01.14.476374<br /><br />Levin, M. O., Meek, J. B., Boom, B., Kross, S. M., & Eskew, E. A. (2022). Using publicly available data to conduct rapid assessments of extinction risk. Conservation Science and Practice, November 2020, 1–9. https://doi.org/10.1111/csp2.12628<br /><br />Montgomery, D. R., Biklé, A., Archuleta, R., Brown, P., & Jordan, J. (2022). Soil health and nutrient density: preliminary comparison of regenerative and conventional farming. PeerJ, 10, e12848. https://doi.org/10.7717/peerj.12848<br /><br />Saran, S., Chaudhary, S. K., Singh, P., Tiwari, A., & Kumar, V. (2022). A comprehensive review on biodiversity information portals. Biodiversity and Conservation, 0123456789. https://doi.org/10.1007/s10531-022-02420-x<br /><br />Sincerely,<br /> <br />Jon<br /> <br />p.s. This photo is of what I think is a bromeliad fly (Copestylum) on a Tradescantia flower in my garden. First time I have seen one!</p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-22508563800760072032022-06-01T08:19:00.001-04:002022-06-01T08:19:00.156-04:00June 2022 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/52040835583/in/datetaken/" title="Red-winged blackbird"><img alt="Red-winged blackbird" height="300" src="https://live.staticflickr.com/65535/52040835583_f9577e66d8_w.jpg" width="400" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script><p>Greetings,</p><p><br />This month I only have three science articles but they're all good'uns.<br /><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a data-cke-saved-href="http://eepurl.com/diB0nr" href="http://eepurl.com/diB0nr">http://b</a><a data-cke-saved-href="http://bit.ly/sciencejon" href="http://bit.ly/sciencejon" target="_blank">it.ly/sciencejon</a> (no need to email me).<br /><br /><strong>PROTECTED AREAS:</strong><br />Sullivan-Stack et al. 2022 is a great summary of marine protected areas (MPAs) in the U.S., and flags that achieving 30% U.S. ocean protection by 2030 is not on track to provide sufficient benefit to marine ecosystems. The key finding that stood out to me was the need for improving both geographic representation and efficacy / strength of protection (as well as climate resilience and equity). U.S. oceans are 26% protected overall (25% fully or highly protected), but 96% of that is in the central Pacific ocean. Excluding that region, only 2% has any protection (and only 22% of that 2% is fully or highly protected). See Table 3 for a summary of how much of each region is protected and at what level (Figure 1 has a map but it's not split by protection strength). Alaska has the lowest % protection of any kind (0.7%) while OR & WA have the weakest protection (4.2% of ocean is protected, but that's all minimal protection). Skip to section 4 for their recommendations: create more effective MPAs (via new ones and strengthening existing ones), improve representation of different marine regions & species & habitats in well-connected MPAs, improve equity & access, go beyond tracking % coverage and include impact assessments, make MPAs durable and climate resilient, coordinate state MPAs, reinstate and empower the MPA Federal Advisory Committee, strengthen & fund the NOAA MPA Center, and update the U.S. National Ocean Policy for holistic ocean planning and management.<br /><br /><br /><strong>ECOSYSTEM INDICATORS:</strong><br />Nicholson et al. 2021 is chock full of useful diagrams and lists. They have a number of recommendations for setting ecosystem goals (which have milestones, targets, and indicators) for a global biodiversity framework, but which can be relevant to other efforts (like 30x30). At a high level they flag the need to track not only total ecosystem/habitat area (or extent), but also changes in ecosystem integrity (including the risk of ecosystem collapse - see Box 2 for definitions). Fig 2 is a nice visual summary of how different types of targets can collectively capture different threats and ecosystem attributes that need to be addressed for long term ecosystem health. Fig 3 is a super helpful review of many different environmental indices / metrics, and what aspects of ecosystems they include and omit. Spend some time with that one - even learning about all of the indices was very helpful for me. They close with 6 recommendations for picking indicators: we need a set of them (no single one suffices), they need to reflect goals (not actions), relevance to the goal is at least as important as data availability, we need more testing and validation of indicators, we need stronger connections between global indicators and national or local policies, and we need new indicators to provide early warning of ecosystem collapse.<br /><br /><br /><strong>ECOSYSTEM CONDITION:</strong><br />There are good remote sensing data for land cover change, worse but decent data for land use change, but generally not much on degradation (which means we can underestimate ecological decline). Swaty et al. 2021 describe a "Vegetation Departure" (VDEP) spatial data set for the US which gets at this. This includes whether early or late successional stages are over-represented or under-represented (think of a logged forest w/ no old growth left but plenty of young forest, or a grassland being taken over by denser shrubs which were historically less common). They highlight several limitations of the existing LANDFIRE VDEP data (which focuses on canopy cover and height), and recommend that users consider other attributes that are important to their ecosystems of interest (e.g., biodiversity, wildlife populations, wildfire risk, etc.).<br /><br /><br /><strong>REFERENCES:</strong></p><p>Nicholson, E., Watermeyer, K. E., Rowland, J. A., Sato, C. F., Stevenson, S. L., Andrade, A., Brooks, T. M., Burgess, N. D., Cheng, S.-T., Grantham, H. S., Hill, S. L., Keith, D. A., Maron, M., Metzke, D., Murray, N. J., Nelson, C. R., Obura, D., Plumptre, A., Skowno, A. L., & Watson, J. E. M. (2021). Scientific foundations for an ecosystem goal, milestones and indicators for the post-2020 global biodiversity framework. Nature Ecology & Evolution, 5(10), 1338–1349. https://doi.org/10.1038/s41559-021-01538-5<br /><br />Sullivan-Stack, J., Aburto-Oropeza, O., Brooks, C. M., Cabral, R. B., Caselle, J. E., Chan, F., Duffy, J. E., Dunn, D. C., Friedlander, A. M., Fulton-Bennett, H. K., Gaines, S. D., Gerber, L. R., Hines, E., Leslie, H. M., Lester, S. E., MacCarthy, J. M. C., Maxwell, S. M., Mayorga, J., McCauley, D. J., … Grorud-Colvert, K. (2022). A Scientific Synthesis of Marine Protected Areas in the United States: Status and Recommendations. Frontiers in Marine Science, 9(May), 1–23. https://doi.org/10.3389/fmars.2022.849927<br /><br />Swaty, R., Blankenship, K., Hall, K. R., Smith, J., Dettenmaier, M., & Hagen, S. (2021). Assessing Ecosystem Condition: Use and Customization of the Vegetation Departure Metric. Land, 11(1), 28. https://doi.org/10.3390/land11010028<br /><br /><br />Sincerely,<br /> <br />Jon<br /> <br />p.s. The photo above is of a red-winged blackbird bathing in the Potomac River at Dyke Marsh</p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0tag:blogger.com,1999:blog-3828861446310385465.post-81685892032436111172022-05-02T08:17:00.002-04:002022-05-02T17:13:48.670-04:00May 2022 science summary<a data-flickr-embed="true" href="https://www.flickr.com/photos/jaundicedferret/51950043532/in/datetaken/" title="Lizard on a porch screen"><img alt="Lizard on a porch screen" height="400" src="https://live.staticflickr.com/65535/51950043532_d24b7a1ef4_w.jpg" width="300" /></a><script async="" charset="utf-8" src="//embedr.flickr.com/assets/client-code.js"></script>
<p>Greetings,</p><p><br />This month I have a few science articles on freshwater, two on climate change and forest management, and one big one on biodiversity.<br /><br />If you know someone who wants to sign up to receive these summaries, they can do so at <a data-cke-saved-href="http://eepurl.com/diB0nr" href="http://eepurl.com/diB0nr">http://b</a><a data-cke-saved-href="http://bit.ly/sciencejon" href="http://bit.ly/sciencejon" target="_blank">it.ly/sciencejon</a> (no need to email me).<br /><br /><strong>BIODIVERSITY:</strong><br />Hamilton et al. 2022 is the latest analysis from NatureServe on biodiversity in the U.S., and potential priorities for new protection. They looked at habitat for 2,216 imperiled species (G1 or G2 globally, or Threatened or Endangered nationally) across the U.S., including often overlooked species like plants and bugs. There are several interesting methodological advances here (relatively fine 1-km pixels, inclusion of overlooked species, using both range maps and habitat suitability models and showing how that changes results in Fig 4, etc.), but I think most readers will want to focus on implications for new protections and management of existing protected areas. Fig 2 shows the most important areas to protect. They use protection-weighted range-size rarity, which is a kind of rarity-weighted richness focusing on places with a) relatively high # of species that b) have relatively little habitat left nationally. Table 2 has a nice summary of how many species have the majority of their habitat managed by different groups (federal agencies, state & local, private), showing there is a lot of potential for management on existing public lands (since 43% of imperiled species have most of their habitat on public lands). It's worth reading the whole thing, but if short on time I recommend the <a href="https://www.nytimes.com/interactive/2022/03/03/climate/biodiversity-map.html">NY Times article about this</a> and especially the <a href="https://livingatlas.arcgis.com/en/browse/?q=mobi#d=2&q=mobi%20owner%3ANatureServe&srt=name">interactive maps of their data</a>.<br /><br /><br /><strong>CLIMATE CHANGE / FOREST MANAGEMENT</strong>:<br />Littlefield and D'Amato 2022 looks at trade-offs between maximizing forest carbon and maximizing biodiversity and habitat quality. In particular, they note that many species require disturbance (like fire or tree removal), while maximizing carbon generally involves promoting uniformly dense and mature trees. They note that robust data looking at how different species respond to forest management are surprisingly scarce, but offer several case studies where as tree biomass increased, wildlife abundance and/or diversity has declined. They recommend that conservation planning consider climate adaptation, which means keeping landscape diversity, complexity, and connectivity (accepting that means some reduction in potential carbon), and that we explicitly discuss and recognize trade-offs where they exist.<br /><br />Stephenson et al. 2014 is a global analysis of how carbon sequestration by 403 tree species change as they grow and age. 87% of tree species sequester more annual carbon per year as they get bigger (even when they get huge). On average a 1m diameter tree sequesters about triple the carbon as a 1/2m diameter tree (similar to the trunk cross-section ration of 4:1). The biggest trees can add ~0.55-0.72 t biomass (not C, which would be much lower) per year (Fig 3). However, they note that at the forest level, as an even-aged stand gets older the annual carbon sequestered per land area goes down (as trees die, total sequestration declines despite remaining big trees sequestering more. Ideally forest management should think about 1) impacts on carbon pools (how much harvested tree biomass will be lost to the atmosphere), 2) impacts on carbon sequestration, and 3) impacts on forest ecology (both mature / older trees, and disturbances and younger trees have important roles).<br /><br /><br /><strong>FRESHWATER</strong>:<br />Broadley et al. 2022 is a global assessment (although w/ ~1/4 of studies coming from the US) of how marine fishery productivity (including invertebrates) depends on rivers. Their headline finding is that 72% of 276 fished species (77% of global catch by mass) are linked to river flows at some point in their life cycle, and 83% eat food linked to river flows. The biggest link is occasionally going to estuaries to eat (77% of species) as opposed to diadromous or estuarine-dependent species (23% of species), see Fig 5 for a map of where they're distributed. They also offer a conceptual review of how rivers influence fisheries by focusing on science literature for the top 10 fishery species by catch mass. They conclude that rivers influence fisheries via physical changes (flow quantity, timing, and quality [sediment, nutrients, salinity, temperature, etc.]), biological response of marine species to those physical changes (e.g. nutrients from a river increasing algae which zooplankton and fish respond to, changes in spawning in response to freshwater mixing, migration, etc.), and changes in fisher behavior and fishery productivity resulting from those biological changes (see Table 1). They recommend an integrated planning approach to rivers (including dam management) and marine fisheries.<br /><br />Pennock et al. 2022 makes a case that rivers with relatively natural flow regimes should be priorities for conservation (specifically protection that limits consumptive water use or otherwise alters flow). They look at four tributaties of the Green River (which feeds the Colorado River): the White, Price, San Rafael, and Duchesne Rivers. Only the White River has a relatively natural flow regime (although median spring discharge is still down 25% relative to before 1949, and summer baseflow by 29%), and spring flow in the Duchesne and San Rafel are down ~80%. That drop in flow accompanies habitat degraded in several ways: less large woody debris, narrower channels, less regeneration of cottonwoods, loss of native fish spp, etc. They also point out that even dams managed for environmental flow has fallen well short of natural flood regimes.<br /><br />Maasri et al. 2022 is a new global freshwater research agenda. They have 15 recommendations in 5 themes: 1) Data infrastructure (compile and integrate data sources on freshwater biodiversity, mobilize and share existing data w/ stakeholders, and develop accessible databases), 2) Monitoring (coordinate existing FW biodiversity monitoring and move towards global consistency, expand monitoring to places and species currently overlooked [like fungi and protists], and develop new monitoring methods [like eDNA, remote sensing, citizen science, etc.]), 3) Ecology (better understand how biodiversity relates to ecosystem health and services, study how biodiversity responds to multiple stressors, and study species and ecosystem responses to global change), 4) Management (rigorous assess how well restoration works, develop management strategies aligned with "Nature Futures" scenarios based on positive human-nature relationships, and develop watershed-based integrated management and restoration programs including dam building and operation), and 5 Social ecology (co-produce solutions to conflicts between conservation and people who use freshwater systems, develop adaptive management strategies that address trade-offs with a broad coalition of participants, and promote citizen science and participatory research). I was surprised that they left off legal research into how policy mechanisms for water management are working (or not), and am somewhat skeptical that agendas like this get used, but it's a nice overview of some needs and gaps.<br /><br /><br /><strong>REFERENCES:</strong></p><p>Broadley, A., Stewart-Koster, B., Burford, M. A., & Brown, C. J. (2022). A global review of the critical link between river flows and productivity in marine fisheries. Reviews in Fish Biology and Fisheries, 0123456789. https://doi.org/10.1007/s11160-022-09711-0<br /><br />Hamilton, H., Smyth, R. L., Young, B. E., Howard, T. G., Tracey, C., Breyer, S., Cameron, D. R., Chazal, A., Conley, A. K., Frye, C., & Schloss, C. (2022). Increasing taxonomic diversity and spatial resolution clarifies opportunities for protecting US imperiled species. Ecological Applications, 32(3), 1–19. https://doi.org/10.1002/eap.2534<br /><br />Littlefield, C. E., & D’Amato, A. W. (2022). Identifying trade‐offs and opportunities for forest carbon and wildlife using a climate change adaptation lens. Conservation Science and Practice, 4(4), 1–14. https://doi.org/10.1111/csp2.12631<br /><br />Maasri, A., Jähnig, S. C., Adamescu, M. C., Adrian, R., Baigun, C., Baird, D. J., Batista‐Morales, A., Bonada, N., Brown, L. E., Cai, Q., Campos‐Silva, J. V., Clausnitzer, V., Contreras‐MacBeath, T., Cooke, S. J., Datry, T., Delacámara, G., De Meester, L., Dijkstra, K. B., Do, V. T., … Worischka, S. (2022). A global agenda for advancing freshwater biodiversity research. Ecology Letters, 25(2), 255–263. https://doi.org/10.1111/ele.13931<br /><br />Pennock, C. A., Budy, P., Macfarlane, W. W., Breen, M. J., Jimenez, J., & Schmidt, J. C. (2022). Native Fish Need A Natural Flow Regime. Fisheries, 47(3), 118–123. https://doi.org/10.1002/fsh.10703<br /><br />Stephenson, N. L., Das, A. J., Condit, R., Russo, S. E., Baker, P. J., Beckman, N. G., Coomes, D. A., Lines, E. R., Morris, W. K., Rüger, N., Álvarez, E., Blundo, C., Bunyavejchewin, S., Chuyong, G., Davies, S. J., Duque, Á., Ewango, C. N., Flores, O., Franklin, J. F., … Zavala, M. A. (2014). Rate of tree carbon accumulation increases continuously with tree size. Nature, 507(7490), 90–93. https://doi.org/10.1038/nature12914<br /><br /><br />Sincerely,<br /> <br />Jon<br /><br /></p>Jonhttp://www.blogger.com/profile/07401406875002489359noreply@blogger.com0