I-Corps: Translation Potential of an Artificial Intelligence (AI) Surrogate for Coastal Storm Surge and Water Level Forecasting

This I-Corps project is based on the development of an artificial intelligence (AI) tool that rapidly predicts storm surge and water levels. Anticipating how high the water will rise during a storm and how likely water levels will reach a severe level at a given location may protect lives and property. Such predictions inform evacuation orders and emergency response, the design of buildings, bridges, ports, and coastal defenses, the pricing and availability of insurance, and the speed with which disaster payouts reach affected households. This technology makes those predictions faster and less expensive by training an AI model on high-resolution simulations. The applications include insurance and reinsurance, engineering and construction, energy and port operations, and public planning. This may provide fast, storm surge and total water level forecasting for organizations that today depend on slow physics-based hydrodynamic simulations to price, manage, or transfer coastal flood risk. This I-Corps project utilizes experiential learning coupled with first-hand investigation of the industry ecosystem to assess the translation potential of an artificial intelligence (AI) surrogate model for storm surge and water level prediction. Storm surge is traditionally predicted by numerical models that solve the governing physical equations on high-performance computers. This approach is expensive and time-consuming, so practitioners often resort to coarser, lower-fidelity models that trade accuracy for speed. This technology uses an AI surrogate trained from high-resolution simulations. Once trained, the surrogate makes predictions far faster and more energy-efficiently, while retaining the fidelity of the simulations used for training. This technology may enable rapid disaster management and large-scale scenario analysis that is essential to risk modeling of extreme storm surge events. 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.