Prediction of Storm Surge Water Level Based on Machine Learning Methods

Abstract

Storm surge disasters result in severe casualties and economic losses. Accurate prediction of storm surge water level is crucial for disaster assessment, early warning, and effective disaster management. Machine learning methods are relatively more efficient and straightforward compared to numerical simulation approaches. However, most of the current research on storm surge water level prediction based on machine learning methods is primarily focused on point predictions. In this study, we explore the feasibility of spatial water level prediction using the ConvLSTM model. We focus on the coastal area of Guangdong Province and employ MIKE21(2019) software to simulate historical typhoons that have made landfall in the region from 1991 to 2018. We construct two datasets: one for direct water level prediction and the other for indirect water level prediction based on water level changes. Utilizing the ConvLSTM network, we employ it to forecast storm surges on both datasets, effectively capturing both temporal and spatial characteristics and thus ensuring the production of dependable results. When directly predicting water levels, we achieve an MAE (mean absolute error) of 0.026 m and an MSE (mean squared error) of 0.0038 m2. In contrast, the indirect prediction approach yields even more promising results, with an MAE of 0.014 m and an MSE of 0.0007 m2. Compared to traditional numerical simulation methods, the ConvLSTM-based approach is simpler, faster, and able to predict water levels accurately without boundary conditions or topographies. Furthermore, we consider worst-case scenarios by predicting the maximum water increase value using the random forest model. Our results indicate that the random forest model can serve as a valuable reference for forecasting the maximum water increase value of typhoon storm surges, supporting effective emergency responses to disasters.