Collaborative research: caig: inferring hidden urban flood controls using physics-informed multimodal learning

The National Science Foundation Office of Integrative Activities awarded the Research Foundation of the City University of New York (doing business as Rfcuny - City College) $349,233 on October 1, 2026, for a collaborative research project on inferring hidden urban flood controls using physics-informed multimodal artificial intelligence.

The project develops an AI framework to estimate flood depth and infer hidden drainage and surface-flow controls in urban stormwater systems by extracting information from unstructured flood evidence—reports, photographs, and videos—rather than relying on sparse direct measurement. Focusing on Greater New York, the work establishes flood datasets and physics-based simulation benchmarks; advances geospatial-aware language and vision technologies to estimate flood depth with quantified uncertainty; designs inversion-enabled surrogate flood models that infer latent controls from sparse depth constraints; and analyzes how inferred controls vary across storms, urban forms, and cities. The research supports flood-risk assessment and infrastructure planning while training students and engaging city agencies in understanding urban flooding and artificial intelligence through shared data, software, and educational outreach.

Performance runs from October 1, 2026, through September 30, 2029, at New York, NY. The award is issued under the Geosciences program (CFDA 47.050), which supports basic research expanding fundamental knowledge of the integrated Earth system. No sub-awards are planned.

Abstract

Urban flooding increasingly threatens infrastructure and communities across the united states, where extreme rainfall interacts with dense built environments and aging stormwater systems. A major challenge is that cities often lack flood-depth information during storms, while many important conditions that control flood response are hidden or rarely measured. This project will investigate how reports, photographs, videos, and other unstructured evidence of flooding can help reveal hidden urban flood controls. The project will support flood-risk assessment and infrastructure planning, while training students, engaging city agencies, and broadening public understanding of urban flooding and artificial intelligence through shared data, software, and educational outreach. This project will develop a physics-informed multimodal artificial intelligence framework for inferring and explaining hidden system controls in urban flooding. Focusing on greater new york, the project will establish flood datasets and physics-based simulation benchmarks; advance geospatial-aware language and vision technologies to estimate flood depth from unstructured evidence with quantified uncertainty; design inversion-enabled surrogate flood models that use sparse depth constraints to infer latent drainage and surface-flow controls; and analyze how inferred controls vary across storms, urban forms, and cities. Together, these efforts will establish a new modeling paradigm for inferring hidden urban flood controls from indirect flood observations. 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.- subawards are not planned for this award.