This project aims to use AI to predict harmful algal blooms in Chesapeake Bay rivers, especially during extreme weather events, to improve early warning and response.
Drinking water systems face growing challenges as extreme weather events increase variability in water quantity and quality. Harmful algal blooms (HABs) are becoming more frequent in the Chesapeake Bay region and pose risks to human health, recreation, and water treatment systems. However, limited data exist on how and where HABs form in nontidal rivers that feed into the Bay, reducing the ability of utilities and agencies to respond proactively. This project will develop an AI-driven predictive model to better understand and forecast river-based HABs under compound hydrological extremes, such as droughts followed by floods. Using datasets from USGS, USDA, and NOAA, the team will identify key environmental drivers and construct a preliminary model linking hydrological conditions to bloom occurrence. By improving prediction and monitoring of HABs in the Chesapeake Bay region, this research aims to support earlier interventions, reduce risks to public health, and strengthen the resilience of regional water systems under increasing climate variability.
