Developing a deep learning-based storm surge forecasting model

Abstract

Storm surge is the anomalous rising of the sea surface induced by intense atmospheric disturbances. The storm surge caused by tropical cyclones often causes great socio-economic, human activity, and life and property hazards to coastal areas. In terms of research resource consumption and computational time, machine learning algorithms that depend on data-driven strong nonlinear mapping skills outperform standard numerical model forecasting. To obtain a lighter and faster storm surge shortcoming forecast, we use a deep learning-based single-station water level prediction model for a storm surge at several locations in this work. In contrast to earlier research, this study employs convolutional neural networks to extract two-dimensional wind field information and merge them with local water level features to produce a more time-efficient intelligent forecast.