Federal Project Grant Award Summary

Florida International University received a $200,000 project grant from the National Science Foundation's Division of Information and Intelligent Systems (CISE program, CFDA 47.070) effective February 1, 2026 through January 31, 2029. This collaborative research initiative develops artificial intelligence and machine learning methods to enhance the management of urban water and wastewater networks. The project deliverables include a computational framework integrating machine learning, graph-based modeling, and multimodal data integration to analyze fragmented water infrastructure data. Key technical products encompass methods for completing and repairing directed network representations using physics-informed flow models and attention-based neural networks, as well as interpretable uncertainty quantification tools to assess confidence in network inferences and identify missing or inconsistent data connections.

The research addresses critical operational challenges in water utility management by transforming scattered, incomplete, and unstructured infrastructure data into coherent integrated network representations. The resulting tools are designed to reduce manual data review requirements, enable early detection of anomalies such as leaks and blockages, and support informed decision-making for utility operators. Through improved data organization and analysis capabilities, the project aims to enhance service reliability, reduce operational costs, and protect public health and environmental quality by preventing costly emergency interventions in aging water infrastructure systems.