Multi-Output Artificial Neural Network for Storm Surge Prediction in North Carolina
This addresses the need for timely storm surge predictions for emergency managers during hurricane seasons, though it appears incremental as it applies an existing neural network method to a specific domain.
The paper tackles the problem of slow storm surge forecasting by developing an artificial neural network model that provides fast, real-time estimates at coastal locations in North Carolina, showing performance comparisons on synthetic and real hurricane data.
During hurricane seasons, emergency managers and other decision makers need accurate and `on-time' information on potential storm surge impacts. Fully dynamical computer models, such as the ADCIRC tide, storm surge, and wind-wave model take several hours to complete a forecast when configured at high spatial resolution. Additionally, statically meaningful ensembles of high-resolution models (needed for uncertainty estimation) cannot easily be computed in near real-time. This paper discusses an artificial neural network model for storm surge prediction in North Carolina. The network model provides fast, real-time storm surge estimates at coastal locations in North Carolina. The paper studies the performance of the neural network model vs. other models on synthetic and real hurricane data.