The presence of Escherichia coli (E. coli) contamination in recreational waterways poses health threats to the public. This danger can be alleviated with a predictive modeling framework that can estimate E. coli contamination risk in recreational waters up to 24 hours in advance with approximately 85% accuracy.

The artificial intelligence (AI)-powered framework developed at Florida A&M University-Florida State University College of Engineering uses environmental and hydrometeorological data to provide early warnings of E. coli contamination in such environments, providing communities a window to act before health risks emerge.

The approach described in Water Research analyzes current and historical environmental data to estimate contamination risk, eliminating the time interval required to receive laboratory results. Inputs include upstream hydrologic conditions, streamflow rates, rainfall totals, turbidity readings and water temperature. By combining these variables, the model can flag elevated E. coli risk with 24 hours advance warning.

The research also highlights how land use changes intensify the environmental drivers of contamination. Urbanization in the Chattahoochee River National Recreation Area (CRNRA) in the northern Georgia study area increased impervious cover from 24% to 28% during 2007 and 2023, altering runoff pathways and escalating contamination dynamics.

“This change led to more polluted runoff and higher and more variable E. coli levels in streams,” said the researchers. “Our findings show that every development decision influences water quality and public health, highlighting the need for green infrastructure.”