Project Grant 2615987

The National Science Foundation Office of Integrative Activities awarded The Research Foundation For The State University Of New York $525,530 on August 15, 2026, under the Geosciences program (CFDA 47.050) for collaborative research advancing long-term temperature reconstruction using physics-informed neural networks through lake model emulation.

The project develops a machine-learning framework to replace traditional physics-based lake models with AI-derived surrogates that dramatically accelerate lake simulations. The team will build a globally generalizable emulator of a widely used lake process model using physics-informed neural networks, develop a generative machine-learning pipeline to downscale model outputs to the spatial and temporal scales required by lake simulations, and couple the emulator with Bayesian calibration, uncertainty quantification, and inverse-modeling methods. The approach transforms sediment core observations collected from lakes worldwide into uniform global temperature data products, enabling inference of local temperature variations over thousands of years. The resulting improved understanding of long-term temperature variability will strengthen the scientific foundation for seasonal and long-term prediction, informing decisions across weather-sensitive sectors of the U.S. economy.

The Research Foundation serves as fiscal agent for the State University of New York system and administers the award on behalf of SUNY institutions, with performance in Buffalo, New York. The period of performance runs from the award date through July 31, 2029. The assistance type is Project Grant.