A Novel Deep Learning Approach For Typhoon-induced Storm Surge Modeling Through Efficient Emulation Of Wind And Pressure Fields

This article explores a different approach for simulating storm surges focusing on the efficient emulation of forcing fields. This approach can be used to study the physics of hydrodynamic responses to typhoons through a standard numerical simulation as well as to operate effectively in a forecasting mode. The article obtains typhoon best track data from the International Best Track Archive for Climate Stewardship (IBTrACS) and resamples the data at one-hour intervals to pair with the NWP model outputs. The NWP model used is the Japanese 55-year Reanalysis (JRA-55) downscaled to a 5-km horizontal resolution.