This Project Grant award from the National Science Foundation's Geosciences Program (CFDA 47.050) provides $353,178 to the University of Florida to develop a transformative AI-based framework for generating high-fidelity, physically consistent, and uncertainty-calibrated geoscience data. The goal is to overcome limitations in observational infrastructure and computational cost to produce enhanced datasets that will support better decision-making in disaster preparedness, emergency response, and infrastructure planning. Key innovations include physics-guided loss functions, text-prompted guidance from expert knowledge, and conformal prediction techniques to provide rigorous confidence intervals. The research will be validated using precipitation datasets from tropical cyclones and wildfires, with the broader impacts including advancing tools for prediction, training interdisciplinary scientists, and releasing open-source software. This award reflects NSF's mission to expand fundamental knowledge and understanding of the integrated Earth system through basic research in atmospheric, earth, and ocean sciences.
Mod # | Description | Reason For Modification | Federal Obligation (Click to sort descending) | Date (Click to sort ascending) |
|---|---|---|---|---|
| Not listed | $353.2k | 7/14/25 |