This article by Alyssa Ozment with photo by Matt Yung first appeared on the Kennesaw State University website, republished with permission

Water is a necessity that humans cannot live without.

Despite this, accurate water quality data is not widely accessible in real-time, which is a detriment that can impact public health and aquatic ecosystems.

Assistant professor of computer science Ahyoung Lee is working to fill in these gaps using a bacterial monitoring and forecasting system that utilizes artificial intelligence (AI), real-time monitoring, and predictive analytics to provide water-quality information and predict potential bacterial outbreaks.

The project, NSF I-Corps: Translation Potential of Artificial Intelligence-Enabled Bacterial Forecasting System for Water Quality Monitoring, blends hands-on learning with a direct investigation of the industry to assess the feasibility of adapting an AI-driven system that predicts bacterial levels for monitoring water quality in real-time.

Lee is looking specifically at Escherichia coli (E. coli) detection. E. coli is common in surface water, with the National Institutes of Health (NIH) noting 25.2% of water supply sources for households are contaminated.

“The bacterial forecasting system helps everyday people by ensuring cleaner and safer water,” Lee said. “By improving water quality and reducing contamination risks, it protects public health and enhances recreational experiences.”

Enhanced recreational experiences include boating, swimming, fishing, and other activities that occur in lakes, rivers, and ponds, which fall into the category of surface water.

While surface water is most prone to contamination, E. coli can be found in groundwater such as private water wells.

“This project also helps lower costs for communities, making water monitoring more efficient and accessible, especially for underserved areas that struggle with water safety issues,” Lee said.

Lee has several students working with her on this project, including a Ph.D. student, a graduate research assistant (GRA) and three undergraduate students who are a part of the First-Year Scholars Program (FYSP).

Ultimately, Lee’s innovative bacterial monitoring and forecasting system represents a significant advancement in real-time water quality tracking. By utilizing AI and predictive analytics, the system not only provides vital water quality data but also helps predict potential bacterial outbreaks at a lower cost than other technologies.