Vulnerability of the rip current phenomenon in marine environments using machine learning models

Abstract

Hidden and perilous rip currents are one of the primary factors leading to drownings of beach swimmers. By identifying the coastal areas with the highest likelihood of generating rip currents, it becomes possible to prevent fatalities and mitigate economic losses associated with these hazardous currents. Rip currents are characterized as streams of water moving towards the open sea, forming within the area where waves break, due to variations in wave-induced radiation stresses and pressure along the coastline. This study utilized nine different Machine Learning (ML) models, including M5 Model Tree (MT), Multivariate Adaptive Regression Spline (MARS), Gene Expression Programming (GEP), Evolutionary Polynomial Regression (EPR), Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), and Stacked ML models, to estimate the Relative Tide Range (RTR) values for 50 southern beaches in China. Through this approach, we gathered a reliable dataset from prior research conducted on the southern coast of China. In this study, two parameters, namely dimensionless fall velocity parameter (Ω) and tide range (TR) are used to predict the vulnerability of rip current event. The results of the AI models were assessed by various statistical analyses (Correlation of Coefficient [R], Root Mean Square Error [RMSE], violin diagram, heatmap, and taylor diagram) for training and testing stages. Accordingly, the MARS model exhibited superior performance compared to other AI models in accurately predicting the RTR value. The outcomes substantiated the significant effectiveness and capability in estimating the RTR with high accuracy. Southern China coasts have relative high risk level of rip current, necessitating the attention and strategic management of this dangerous current by the beach managers.