Promoting equity in the use of algorithms for high-seas conservation

Chapman, Melissa; Oestreich, William K.; Frawley, Timothy H.; Boettiger, Carl; Diver, Sibyl; Santos, Bianca Silva; Scoville, Caleb; Armstrong, Katrina; Blondin, Hannah; Chand, Kevin; Haulsee, Danielle E.; Knight, Christopher J.; Crowder, Larry B.

doi:10.1016/j.oneear.2021.05.011

Cited by 8 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…104 Although the emergence of the digital ocean ecosystem has led to unquestionable scientific advances, it has also raised concerns regarding the equity of dataprocessing algorithms, the control of information flows, and the determination of research priorities. 23,[109][110][111] With big ocean data restructuring the relationships between scientists, policymakers, and fisheries stakeholders, the resulting reconfiguration of power may be irreducible to whose interests are served. 112,113 Moving forward, policymakers and governments should identify strategies to diversify who benefits from the digital ocean ecosystem, empowering fishers and non-state groups such as RFMOs that may be unable to finance cutting-edge technology.…”

Section: Big Ocean Data and Pacific Fisheries Governancementioning

confidence: 99%

Clustering of disaggregated fisheries data reveals functional longline fleets across the Pacific

Frawley

Muhling²,

Welch³

et al. 2022

One Earth

Self Cite

View full text Add to dashboard Cite

Section: Big Ocean Data and Pacific Fisheries Governancementioning

confidence: 99%

Clustering of disaggregated fisheries data reveals functional longline fleets across the Pacific

Frawley

Muhling²,

Welch³

et al. 2022

One Earth

Self Cite

View full text Add to dashboard Cite

“…Reward misspecification is not unique to RL and has long been a central problem in ecological management and decision‐making (Conroy & Peterson, 2013; Gregory et al, 2012), but it is important to make clear that RL does not resolve this issue. A greater role of algorithms in conservation decision‐making also raises questions about ethics and power, particularly when those algorithms are opaque or proprietary (Chapman et al, 2021; Scoville et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

Deep reinforcement learning for conservation decisions

et al. 2022

Self Cite

View full text Add to dashboard Cite

1. Can machine learning help us make better decisions about a changing planet?In this paper, we illustrate and discuss the potential of a promising corner of machine learning known as deep reinforcement learning (RL) to help tackle the most challenging conservation decision problems. We provide a conceptual and technical introduction to deep RL as well as annotated code so that researchers can adopt, evaluate and extend these approaches.2. RL explicitly focuses on designing an agent who interacts with an environment that is dynamic and uncertain. Deep RL is the subfield of RL that incorporates deep neural networks into the agent. We train deep RL agents to solve sequential decision-making problems in setting fisheries quotas and managing ecological tipping points.3. We show that a deep RL agent is able to learn a nearly optimal solution for the fisheries management problem. For the tipping point problem, we show that a deep RL agent can outperform a sensible rule-of-thumb strategy. 4. Our results demonstrate that deep RL has the potential to solve challenging decision problems in conservation. While this potential may be compelling, the challenges involved in successfully deploying RL-based management to realistic scenarios are formidable-the required expertise and computational cost may place these applications beyond the reach of all but large, international technology firms. Ecologists must establish a better understanding of how these algorithms work and fail if we are to realize this potential and avoid the pitfalls such a transition would bring. We ultimately set forth a research framework based on well-posed, public challenges so that ecologists and computer scientists can collaborate towards solving hard decision-making problems in conservation.

show abstract

“…Such framings could be very harmful, because they would implicitly de-legitimize the value of traditional and expert knowledge, and could further support the long legacy of colonialism and white supremacy in ecology, e.g. (77, 78). We suggest that instead it would be best to apply future and more powerful versions of LOVE to real-world problems only when the nature of the problem to be solved has been co-identified in consultations with relevant communities, and with full consideration of the unintended consequences of algorithm deployment.…”

Section: Discussionmentioning

confidence: 99%

“…Potential LOVE applications must also consider whether they take a technocratic and algorithm-first approach to mediating relationships between people and nature. Such framings could be harmful because they would de-legitimize the value of traditional and expert knowledge, and could support the legacy of colonialism and white supremacy in ecology (Chapman et al 2021;Wyborn & Evans 2021). Real applications of LOVE should include engaging relevant communities, and consideration of the unintended consequences of algorithm deployment.…”

Section: Ethical Considerationsmentioning

confidence: 99%

Predicting and prioritizing community assembly: learning outcomes via experiments

Blonder

Godoy

2022

Preprint

View full text Add to dashboard Cite

Predicting species coexistence can be difficult often because underlying assembly processes are unknown and data are limited. However, accurate predictions are needed for design and forecasting problems in biodiversity conservation, climate change, invasion ecology, restoration ecology, and synthetic ecology. Here we describe an approach (Learning Outcomes Via Experiments; LOVE) where a limited set of experiments are conducted and multiple community outcomes measured (richness, composition, and abundance), from which a model is trained to predict outcomes for arbitrary experiments. Across seven taxonomically diverse datasets, LOVE predicts test outcomes with low error when trained on ~100 randomly-selected experiments. LOVE can then prioritize experiments for tasks like maximizing outcome richness or total abundance, or minimizing abundances of unwanted species. LOVE complements existing mechanism-first approaches to prediction and shows that rapid screening of communities for desirable properties may become possible.

show abstract

Promoting equity in the use of algorithms for high-seas conservation

Cited by 8 publications

References 13 publications

Clustering of disaggregated fisheries data reveals functional longline fleets across the Pacific

Clustering of disaggregated fisheries data reveals functional longline fleets across the Pacific

Deep reinforcement learning for conservation decisions

Predicting and prioritizing community assembly: learning outcomes via experiments

Contact Info

Product

Resources

About