Image
Research
Machine Learning Reveals which Streams and Wetlands are Protected — or Not — by Shifting Clean Water Act Regulations
UMass Amherst researcher helps develop model that identifies the jurisdictional reach of the Clean Water Act
The 1972 Clean Water Act protects the “waters of the United States” but does not precisely define which streams and wetlands this phrase covers, leaving it to presidential administrations, regulators and courts to decide. As a result, the exact coverage of Clean Water Act rules is difficult to estimate.
New research co-authored by David Keiser, professor of resource economics at the University of Massachusetts Amherst, used machine learning to more accurately predict which waterways are protected by the Act. The analysis, conducted by researchers at the University of California, Berkeley, California Institute of Technology, MIT and UMass Amherst found that a 2020 Trump administration rule removed Clean Water Act protection for one-fourth of wetlands and one-fifth of streams in the U.S., and also deregulated 30% of watersheds that supply drinking water to household taps.
“The Clean Water Act is the foundational law that protects the quality of our rivers, streams, lakes and wetlands. It is shocking that for 50 years, we have had very little ability to comprehensively identify what resources the act protects,” Keiser said.
“Using machine learning to understand these rules helps decode the DNA of environmental policy,” added author Joseph Shapiro, an associate professor of Agricultural and Resource Economics at UC Berkeley. “We can finally understand what the Clean Water Act actually protects.”
The Clean Water Act is the foundational law that protects the quality of our rivers, streams, lakes and wetlands. It is shocking that for 50 years, we have had very little ability to comprehensively identify what resources the act protects.
David Keiser, professor of resource economics at UMass Amherst
Prior analyses assumed that streams and wetlands sharing certain geophysical characteristics were regulated, without scrutinizing data on what was actually regulated — an approach the Environmental Protection Agency and Army Corps of Engineers called “highly unreliable.”
The researchers trained a machine learning model to predict 150,000 jurisdictional decisions by the Army Corps. Each Corps decision interprets the Clean Water Act for one site and rule. The model predicts regulation across the U.S. under the Trump rule and its predecessor, the Supreme Court’s Rapanos ruling, which had previously guided Corps decisions.
The research found that the 2020 rule deregulated 690,000 stream miles, more than every stream in California, Florida, Illinois, New York, Ohio, Pennsylvania and Texas combined. The wetlands deregulated under the 2020 rule provided over $250 billion in flood prevention benefits to nearby buildings, the study estimated.
“This game of regulatory ping-pong has staggering effects on environmental protection,” said author Simon Greenhill, a doctoral candidate at UC Berkeley.
The study estimates that the model’s predictions could save over $1 billion annually in permitting costs for regulators and developers by providing immediate estimates of the probability that a site is regulated, rather than waiting months through the uncertain permitting process.
After this study’s data, the 2023 Biden White House rule expanded Clean Water Act jurisdiction and the Supreme Court’s 2023 Sackett decision then contracted it. Once Sackett is fully implemented, this machine learning methodology can clarify its scope.
In a research analysis published in 2021 in “Science,” nine scholars including Keiser contended that a federal water rule enacted in 2020 did not adequately account for transboundary pollution across state lines.