Machine-Learning-Based Model for Hurricane Storm Surge Forecasting in the Lower Laguna Madre

Abstract

During every Atlantic hurricane season, storms represent a constant risk to Texan coastal communities and other communities along the Atlantic coast of the United States. A storm surge refers to the abnormal rise of sea water level due to hurricanes and storms; traditionally, hurricane storm surge predictions are generated using complex numerical models that require high amounts of computing power to be run, which grow proportionally with the extent of the area covered by the model. In this work, a machine-learning-based storm surge forecasting model for the Lower Laguna Madre is implemented. The model considers gridded forecasted weather data on winds and atmospheric pressure over the Gulf of Mexico, as well as previous sea levels obtained from a Laguna Madre ocean circulation numerical model. Using architectures such as Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) combined, the resulting model is capable of identifying upcoming hurricanes and predicting storm surges, as well as normal conditions in several locations along the Lower Laguna Madre. Overall, the model is able to predict storm surge peaks with an average difference of 0.04 m when compared with a numerical model and an average RMSE of 0.08 for normal conditions and 0.09 for storm surge conditions.

A Review of Application of Machine Learning in Storm Surge Problems

“…The cell state is the pathway for information transfer, allowing it to be passed on through the sequence. A host of studies have explored the potential of LSTM for predicting storm surges and have demonstrated that LSTM models can effectively capture temporal patterns and dependencies between sequential values [46,47,49,64,81,92,100,102,[128][129][130]. For instance, Wei and Nguyen [87] proposed an encoder-decoder LSTM neural network model for predicting time-varying storm surges, showcasing its versatility in predicting storm surges generated by bypassing and landfalling storms of different sizes and intensities.…”

“…The featured convolutional layers have multiple kernels to extract useful spatial information from the input data. Many studies have utilized CNNs for storm surge prediction [47,48,78,92,129,130]. For instance, Tiggeloven et al [92] showed that CNNs could be enhanced the most when increasing the number of spatial footprints or hidden layers in the model architecture and outperforming LSTMs.…”

“…The output of the CNN layers is then pooled and passed to a dense layer for the final prediction. It was demonstrated that the CNN+LSTM model was able to emulate future harmonic oscillations from prior observations when accounting for normal atmospheric conditions compared to a single CNN or LSTM architecture [129].…”