Machine learning predicts which rivers, streams, and wetlands the Clean Water Act regulates

Simon Greenhill; Hannah Druckenmiller; Sherrie Wang; David A Keiser; Manuela Girotto; Jason K Moore; Nobuhiro Yamaguchi; Alberto Todeschini; Joseph S Shapiro

doi:10.1126/science.adi3794

Machine learning predicts which rivers, streams, and wetlands the Clean Water Act regulates

Science. 2024 Jan 26;383(6681):406-412. doi: 10.1126/science.adi3794. Epub 2024 Jan 25.

Authors

Simon Greenhill^{1

2}, Hannah Druckenmiller^#^{3

4}, Sherrie Wang^#^{2

5

6}, David A Keiser^{7

8

9}, Manuela Girotto¹⁰, Jason K Moore¹¹, Nobuhiro Yamaguchi¹², Alberto Todeschini¹², Joseph S Shapiro^{1

9

13}

Affiliations

¹ Department of Agricultural and Resource Economics, University of California, Berkeley, Berkeley, CA 94720, USA.
² Goldman School of Public Policy, University of California, Berkeley, Berkeley, CA 94720, USA.
³ Resources for the Future, Washington, DC 20036, USA.
⁴ Division of Humanities and Social Sciences, California Institute of Technology, Pasadena, CA 91125, USA.
⁵ Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
⁶ Institute for Data, Systems, and Society, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
⁷ Department of Resource Economics, University of Massachusetts, Amherst, Amherst, MA 010013, USA.
⁸ Center for Agricultural and Rural Development, Iowa State University, Ames, IA 50011, USA.
⁹ National Bureau of Economic Research, Cambridge, MA 02139, USA.
¹⁰ Department of Environmental Science, Policy, and Management, University of California, Berkeley, Berkeley, CA 94720, USA.
¹¹ US Department of Energy, Washington, DC 20585, USA.
¹² School of Information, University of California, Berkeley, Berkeley, CA 94720, USA.
¹³ Department of Economics, University of California, Berkeley, Berkeley, CA 94720, USA.

^# Contributed equally.

Abstract

We assess which waters the Clean Water Act protects and how Supreme Court and White House rules change this regulation. We train a deep learning model using aerial imagery and geophysical data to predict 150,000 jurisdictional determinations from the Army Corps of Engineers, each deciding regulation for one water resource. Under a 2006 Supreme Court ruling, the Clean Water Act protects two-thirds of US streams and more than half of wetlands; under a 2020 White House rule, it protects less than half of streams and a fourth of wetlands, implying deregulation of 690,000 stream miles, 35 million wetland acres, and 30% of waters around drinking-water sources. Our framework can support permitting, policy design, and use of machine learning in regulatory implementation problems.

MeSH terms

Conservation of Natural Resources
Drinking Water* / legislation & jurisprudence
Machine Learning*
Rivers*
Water Pollution* / legislation & jurisprudence
Water Pollution* / prevention & control
Water Quality*
Wetlands*

Substances

Drinking Water

Grants and funding

R01 AG079914/AG/NIA NIH HHS/United States