Implementation of an Artificial Neural Network to Forecast Storm Surge Time Series

Accurate and timely storm surge forecasts are required during tropical cyclone events to assess the magnitude and location of the storm surge impacts. Dynamical models provide accurate measures of storm surge but are too computationally expensive to be run for real-time forecasting purposes. Real-time forecasting of storm surge impacts is usually conducted by means of a parametric vortex model, implemented within a hydrodynamic model, which decreases computational time at the expense of increased uncertainty. This work seeks to build an artificial neural network, based on modeled data, to forecast storm surge time series in a timely manner, as such needed for real-time forecasting. The model was trained with modeled data resulting from coupling of the Hybrid WRF cyclone model (HWCM) and the Advanced Circulation Model (ADCIRC). An ensemble of synthetic, but physically plausible, cyclones was simulated using the Hybrid WRF cyclone model, and used as input for the hydrodynamic model. Tests of the artificial neural network will be conducted to determine the different number and types of input variables to be used, and different lead-time configurations needed to minimize storm surge forecast errors. Results will provide an insight into the variables needed to achieve timely and accurate storm surge estimates.