As anyone who has driven down California’s I-5 just above Bakersfield can attest, intensive livestock farming is smelly. But the smell from all those cows is not the worst of it. According to the Environmental Protection Agency (EPA), agriculture is the leading contributor of pollutants into the nation’s water supply, with substantial pollution believed to be emanating from large-scale, concentrated animal feeding operations known as CAFOs.
Identifying these farms is key to solving this and other environmental problems they create, but regulators lack vital tools to locate them. As the Government Accountability Office (GAO) reports, no federal agency has reliable information on the number, size, and location of large-scale agricultural operations. Daniel Ho, the William Benjamin Scott and Luna M. Scott Professor of Law, professor (by courtesy) of political science, and a senior fellow at the Stanford Institute for Economic Policy Research, working with PhD student and former SLS fellow Cassandra Handan-Nader, decided to try to solve that challenge by using artificial intelligence (AI).
“This information deficit stifles enforcement of the environmental laws of the United States,” Ho says. Some environmental and public interest groups have tried to identify facilities themselves by scanning terrain manually or poring over aerial photos, but they have found it an incredibly time-intensive task. It took one environmental group more than three years to look at images from just one state. Monitoring efforts like these could never scale or be done in real time, according to Ho.
Using AI machine learning, Ho and Handan-Nader have figured out a way to teach computers how to identify and analyze patterns in data to efficiently locate industrial animal operations and help regulators determine each facility’s environmental risk. The findings were published April 8 in Nature Sustainability.
Satellite imagery and methods for analyzing them are rapidly improving, offering tantalizing opportunities for law and public policy. “Our work shows how a government agency can leverage rapid advances in computer vision to protect clean water more efficiently,” says Ho.