CAREER: Data-Driven Prioritization and Control of Disinfection Byproducts in Drinking Water

About This Grant

Drinking water is important for our health. Disinfection helps keep the water safe and clean. However, some disinfection byproducts (DBPs) can be harmful. These DBPs form when water treatment plants use chemicals like chlorine to kill germs. There are many different DBPs, and identifying all of them would be costly and difficult for water treatment plants. This project will use machine learning (ML) to identify the toxicity of DBPs in drinking water and develop strategies for reducing the presence of high-risk DBPs in drinking water treatment. The results from the project will improve drinking water safety and public health. The project will train students to use AI and data to solve problems of water quality. The project will mentor graduate and undergraduate students at South Dakota School of Mines and Technology, preparing them for future careers in science, engineering, and data science. Disinfection byproducts (DBPs) are a group of chemicals formed during the water disinfection process when disinfectants such as chlorine react with organic matter in water. These chemicals are often toxic and present in treated drinking water. The considerable number of DBPs, coupled with limited data on their occurrence and toxicity, complicates efforts to determine which DBPs should be prioritized for future studies and regulations. Current methods for assessing DBP risks rely on limited occurrence and toxicological data and thus face challenges in effectively identifying which DBPs need the most attention. This project will integrate machine learning (ML) and laboratory experiments to (1) create a databases for both regulated and unregulated DBPs, addressing critical gaps in available occurrence and toxicity data, (2) prioritize high-risk DBPs by analyzing their occurrence frequency, levels, and toxicity, based on their potential health impacts, and (3) develop predictive tools for high-risk DBPs, enabling more informed decision-making for future regulations and water treatment strategies. The results of the project will contribute to minimizing harmful DBPs in drinking water and improving public health. The educational activities from this project include creating student-led STEM summer camps for K-12 students, developing scaffolded educational modules to develop ML literacy in students, and conducting workshops for students on navigating graduate studies. The successful completion of this project will help advance the design and implementation of data-driven solutions in environmental engineering, contributing to improved water quality, public health, and the development of future scientific leaders. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.