Adoption of Artificial Intelligence in Drinking Water Operations: A Survey of Progress in the United States

In recent years, a vision has been shared of how artificial intelligence (AI) can optimize the increasingly complex operations of drinking water utilities. However, it has been unclear if and how water utilities use the technology. Here, we surveyed a simple random sample of 49 large US water utilities to provide a snapshot of progress. We found that 12 of them (24%) have used some form of AI. Of those that have not, the majority plan to use or may plan to use AI in the next 5 years. The reported AI uses were experimental, manual, or partial models rather than fully integrated, ongoing applications. Respondents are motivated to use AI for improving water quality, detecting leaks, and automating complex systems, but they cited payback uncertainty and lack of AI expertise as the most common barriers to implementation. To better demonstrate how AI can join other tools available to assist human operators, researchers should focus on the top motivations and barriers identified here and partner with water utilities on convincing case studies of full-scale AI projects. These steps will support further responsible adoption of AI to optimize water utility operations as part of more sustainable communities.