Monday, May 1, 2023

May 2023 science summary

Nut Case by Katie Hudnall

Greetings,

Does spring feel like it came early or late? It's not just you! DC leafed out 3 weeks ahead of schedule.

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.

If you know someone who wants to sign up to receive these summaries, they can do so at http://bit.ly/sciencejon (no need to email me).

CLIMATE CHANGE & WILDLIFE:
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.


WILDLIFE AND ASSISTED MIGRATION:

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.


FORESTS & FIRE:
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.


FISHERY MANAGEMENT:
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.

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).

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.


REFERENCES:
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

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

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

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

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

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

Sincerely,
 
Jon
 

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.” '

Monday, April 3, 2023

April 2023 science summary

Snake

Hello,

In case you missed it last month, check out the paper I co-authored on gender equity (I repeated the summary below, read or skim the whole paper if you have time, or at least read this blog overview).

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.

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):

  1. Senior Officer, Clean Grid and Energy

    https://pewtrusts.wd5.myworkdayjobs.com/TrustsExternal/job/Washington-DC-901-E/Senior-Officer--Clean-Grid---Energy_R002036

  2. Officer, State Campaigns

    https://pewtrusts.wd5.myworkdayjobs.com/TrustsExternal/job/Washington-DC-901-E/Officer--State-Decarbonization-Campaign-Lead_R002067

  3. Senior Associate, State Campaigns

    https://pewtrusts.wd5.myworkdayjobs.com/TrustsExternal/job/Washington-DC-901-E/Senior-Associate--State-Decarbonization-Campaigner_R002086


Also - recently I am playing less w/ AI and reading more science myself, but thought this was a nice overview of strengths and weaknesses between ChatGPT, Bing, and Bard.


If you know someone who wants to sign up to receive these summaries, they can do so at http://bit.ly/sciencejon (no need to email me).

CLIMATE CHANGE (IPCC report):

The IPCC's latest report (the AR6 synthesis) recently became available (here’s a direct link to the 36 page summary for policy makers). 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:

  1. The planet has warmed 1.1 degrees C already (1.6C on land)

  2. The world is currently roughly on track for 3.2 C of warming based on implemented policies (Fig SPM5a, w/ range from 2.2C to 3.5C).

  3. Good news - that means that "business as usual" is a little worse than RCP4.5 (Intermediate Emissions), ranging from Working Group III scenarios C5 to C7 (C7=High GHG emissions or SSP3-7.0). The high emissions (RCP8.5) scenario is pretty unlikely since it would require emissions to go up substantially over what is predicted. See Table 1 in Box SPM.1 for details.

  4. Bad news - look more closely at Fig SPM5a. The paths to limit warming to 2C or 1.5C assume sharp cuts starting in 2020, which means even if we act immediately, cuts would have to be much sharper 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.

  5. They project climate impacts on species loss, human health, and food production (see Figure SPM3).

I was struck by two quotes in particular:

“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.”

“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).

The press release 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 blog post highlights existing progress and what we need to do next.

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: "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.” (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: "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."

CLIMATE CHANGE (other):

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.

BIODIVERSITY:

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.

WILDLIFE MANAGEMENT:

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.

WILDLIFE VEHICLE COLLISIONS / ROADKILL:

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).


GENDER AND CONSERVATION (REPEAT FROM LAST MONTH):
James et al. 2023 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: https://bit.ly/TNCgenderpaper or a short blog at https://blog.nature.org/science-brief/gender-bias-holds-women-back-in-conservation-careers/


REFERENCES:

IPCC (2023). AR6 Synthesis Report. https://www.ipcc.ch/report/ar6/syr/ (accessed Mar 24, 2023).

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

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

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

NatureServe. (2023). Biodiversity in Focus: United States Edition. https://www.natureserve.org/sites/default/files/NatureServe_BiodiversityInFocusReport_medium.pdf

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


Sincerely,

Jon

p.s. The photo is of a dead copperhead I found on a road near Luray, VA

Friday, March 3, 2023

New paper on gender equity

In case you missed it in my February 2023 science summary, a new paper I co-authored on gender equity came out recently (James et al. 2023). Here's a quick summary:

James et al. 2023 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). 

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. 

You can read it at: https://bit.ly/TNCgenderpaper and there's a short blog at at https://blog.nature.org/science-brief/gender-bias-holds-women-back-in-conservation-careers/



Wednesday, March 1, 2023

March 2023 science summary

Vader trying to play while I work

Happy March!

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 read the whole paper if you have time, or at least read this blog overview.

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 here. 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 guide to things to use AI for (thanks to Bob Lalasz for sending it).

If you know someone who wants to sign up to receive these summaries, they can do so at http://bit.ly/sciencejon (no need to email me).

GENDER AND CONSERVATION:
James et al. 2023 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: https://bit.ly/TNCgenderpaper or a short blog at https://blog.nature.org/science-brief/gender-bias-holds-women-back-in-conservation-careers/ 


AI RESEARCH TOOLS:
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 italics.

Bradford et al. 2019. Soil carbon science for policy and practice. PAPER BLOG
Elicit summary: "Controversy about the role soils might play in climate change mitigation is undermining actions to restore soils for improved agricultural and environmental outcomes."
Jon comments on summary: 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.
Elicit detailed summary: "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." I really like this summary.
Jon comments on other findings: 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.
Jon's open question: "What does building soil carbon do?" 
Answer: "Building soil carbon increases yields and reduces erosion." That is pulled from the paper and is accurate.

Fisher et al. 2018. Impact of satellite imagery spatial resolution on land use classification accuracy and modeled water quality. PAPER BLOG
Elicit summary: "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."
Jon comments on summary: 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)."
Elicit detailed summary: "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." This is the key result, but the more interesting implication is how that wouldn't have affected the decision the research was meant to inform.
Jon comments on other findings:
The test and outcomes were good, the answer to "who were the participants" was "Brazil" 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.
Jon's open question: "When is it good to use low resolution data?"
Answer: "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." 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.

Fisher / Wood / Bradford / Kelsey 2020 (we had equal contributions). Improving scientific impact: How to practice science that influences environmental policy and managementPAPER BLOG
Elicit summary: "Scientists who want to improve the impact their research has on decision-making should identify and understand the audience."
Jon comments on summary: 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"
Elicit detailed summary: "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." Yup - that's a good summary albeit almost a direct quote!
Jon comments on other findings
: N/A (nothing was interesting enough to discuss)
Jon's open question: "Why should scientists read this paper?"
Answer: "The paper provides advice on how to make sure that 1's research has the desired impact." 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.

James et al. 2022. Gender and conservation science: Men continue to out-publish women at the world’s largest environmental conservation non-profit organizationPAPER BLOG
Elicit summary: "The proportion of women to men remains below gender parity at TNC."
Jon comments on summary: 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.
Elicit detailed summary: "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." This is a good summary and includes probably the most important high level result.
Jon comments on other findings: The question "what did they test" answers "The duration is 1968-2019" (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 (# women publishing at TNC, proportion of women:men publishing at TNC, proportion of women from the Global South publishing at TNC) are incomplete but true. It didn't find the 3 citations Google know about.
Jon's open question: "How can gender equity in science publishing be improved?"
Answer: "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." 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.

James et al. 2023. Gender bias and inequity holds women back in their conservation careersPAPER
Elicit summary: "Gender bias and inequity holds women back in their conservation careers."
Jon comments on summary: 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"?
Elicit detailed summary: "This paper discusses how gender bias and inequity affects women in their conservation careers." I actually think the title is still about as good as this one.
Jon comments on other findings: 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.
Jon's open question: "What are ways to improve gender equity?"
Answer: "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" 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."

Kroeger et al. 2014. Reforestation as a novel abatement and compliance measure for ground-level ozone. PAPER BLOG
Elicit summary: "Reforestation is a novel abatement and compliance measure for ground-level ozone."
Jon comments on summary: 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."
Elicit detailed summary: For some reason Elicit declined to produce a detailed abstract summary for this one, I have no idea why!
Jon comments on other findings: 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.
Jon's open question: "What is the national potential for reforestation to abate ozone?"
Answer: "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."

Mcdonald et al. 2009. Urban effects, distance, and protected areas in an urbanizing worldPAPER
Elicit summary: "The median distance from a park to an urban area is already less than 50 km in many regions."
Jon comments on summary: 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."
Elicit detailed summary: "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." Not bad, I like my summary better but this is still good.
Jon comments on other findings: 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!
Jon's open question: "What were the most common threats cities posed to nature?"
Answer: "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."." 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."

Reddy et al. 2017. Advancing Conservation by Understanding and Influencing Human Behavior. PAPER  
Elicit summary: "Integrating two or more behavior change approaches that target multiple, context-dependent factors may be most successful."
Jon comments on summary: 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."
Elicit detailed summary: "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." This is a good summary, no complaints.
Jon comments on other findings: The measured outcomes were wrong, but they got the funding source right (it was in the acknowledgments).
Jon's open question: "What kinds of behavior change interventions use incentives?"
Answer: "The paper mentions that incentives are 1 of 3 behavior change approaches." 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.


REFERENCES:

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

Sincerely,
 
Jon
 
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.

Wednesday, February 1, 2023

February 2023 science summary

Gyokuro green tea on vacation

Hi all,

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.

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!

I'd love to hear what others think about the ChatGPT summaries, and what your own experience playing with it has been.


METASCIENCE:
Jon's summary:
Breznau et al. 2022 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!
ChatGPT's summary:
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.


PEOPLE AND NATURE:
Jon's summary:
Chaplin-Kramer et al. 2022 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.
ChatGPT's summary:
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.

Jon's summary:
Salvatori et al. 2023 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.
ChatGPT's summary:
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.


WILDLIFE CONNECTIVITY
Jon's summary:
Newmark et al. 2023
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.
ChatGPT's summary:
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.


REFERENCES:
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

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.     

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

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


Sincerely,
 
Jon
 
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.



Tuesday, January 3, 2023

Best of 2022 science summary

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.

Happy New Year!


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!


CONSERVATION PRIORITIES / 30x30:
Biodiversity
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 NY Times article about this (https://www.nytimes.com/interactive/2022/03/03/climate/biodiversity-map.htm) and especially the interactive maps of their data online at https://livingatlas.arcgis.com/en/browse/?q=mobi#d=2&q=mobi%20owner%3ANatureServe&srt=name
 
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.


Climate adaptation
Dreiss et al. 2022 identifies priority conservation locations within the contiguous US to support climate adaptation (via refugia and corridors). 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.
 
Climate mitigation:
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!
 
Marine
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.


 
Multiple goals
Dreiss & Malcom 2022 is an analysis of U.S. priorities for protection under 30x30, 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 https://arcg.is/0SjGLK. 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.
 
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 (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: https://www.linkedin.com/posts/sciencejon_conservation-science-goalsetting-activity-6948122284528197632-OH0S/
 



PROTECTED AREAS EFFECTIVENESS:
Sze et al. 2021 compares deforestation and degradation on protected Indigenous lands, 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.


ECOSYSTEM INDICATORS:
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).

Nicholson et al. 2021 is chock full of useful diagrams and lists for ecosystem indicators. 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.

EQUITY:
Fire management & Race
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.: https://www.nytimes.com/interactive/2022/05/16/climate/wildfire-risk-map-properties.html


Gender and Science
James et al. 2022 is an analysis of how gender relates to scientific publication at The Nature Conservancy (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).
You can read blogs about the article at https://www.nature.org/en-us/newsroom/published-science-gender-gap/ and https://blog.nature.org/science/science-brief/conservation-science-publishing-has-a-gender-problem/


FRESHWATER CONSERVATION:
Higgins et al. 2021 offers a very helpful framework for how to effectively conserve freshwater ecosystems. 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 https://jvhiggins.com/


FOOD / AGRICULTURE:
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.



CLIMATE MITIGATION – PEATLANDS:
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.






REFERENCES:
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/

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. https://doi.org/10.1111/csp2.603

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. https://doi.org/10.1111/conl.12849

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. https://doi.org/10.1088/1748-9326/ac4f8c

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

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

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. https://doi.org/10.3390/su13041950

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. https://doi.org/10.1111/csp2.12748

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

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

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

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
 
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

Sze, J. S., Carrasco, L. R., Childs, D., & Edwards, D. P. (2021). Reduced deforestation and degradation in Indigenous Lands pan-tropically. Nature Sustainability, 2. https://doi.org/10.1038/s41893-021-00815-2
 
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. https://doi.org/10.1111/conl.12907


Happy New Year,

Jon

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.