Will algorithms save our planet and will we regret it when they do?
We live in a time of unprecedented global environmental and ecological change: a warming planet, vanishing biodiversity, overfishing and intensifying ecosystem change from fire to draught to invasive species. Not only are these challenges frequently intertwined, all are closely coupled to social, economic, political components which play out in diverse and unequal ways. At the same time, we suddenly have access to ecological and environmental data at a scale we never imagined, thanks to revolutionary technology ranging from satellites to drones to environmental DNA sequencers, opening the door to entirely new approaches for preserving and managing ecosystems and natural resources that are dynamic, highly tuned and spatially varying -- in short, to conservation by algorithm. I will present our work on how algorithmic approaches from artificial intelligence, such as deep reinforcement learning, can allow us to crack some long-standing problems and guide us to some improved ecological outcomes while also highlighting the many open and unsolved challenges. While algorithms which prevent poaching or preserve critical habitat of our non-human co-inhabitants may seem insulated from concerns of equity, racism, and bias so familiar when working with data about humans, such efforts have very real social, economic and political consequences which are easily overlooked, unintended, or undesirable. I will highlight recent collaborations with social scientists, political ecologists, ethicists and others to illuminate when the hardest question is not can we but should we.
Carl Boettiger is an Assistant Professor in the Department of Environmental Science, Policy and Management at UC Berkeley. I work on problems in ecological forecasting and decision making under uncertainty, with applications for global change, conservation and natural resource management. I am particularly interested in how we can predict or manage ecological systems that may experience regime shifts: sudden and dramatic changes that challenge both our models and available data. The rapid expansion in both computational power and the available ecological and environmental data enables and requires new mathematical, statistical and computational approaches to these questions. Ecology has much to learn about what are and are not useful from advances in informatics & computer science, just as it has from statistics and mathematics. Traditional approaches to ecological modeling and resource management such as stochastic dynamic systems, Bayesian inference, and optimal control theory must be adapted both to take advantage of all available data while also dealing with its imperfections. My approach blends ecological theory with the synthesis of heterogeneous data and the development of software – a combination now recognized as data science.