Prediction of Wave Overtopping Characteristics at Coastal Flood Defences Using Machine Learning Algorithms: A Systematic Rreview

Abstract

Abstract The assessment of coastal defences requires reliable prediction of mean overtopping discharges and acceptable overtopping rates for defined design conditions, an process of increasing importance given that global and regional climate change and associated sea level rises are becoming more acute. Prediction of overtopping discharge is usually computed from physical, analytical, and numerical models. However, the ongoing development of soft computing techniques now offer potential for rapid, relatively simple, and economically attractive methods for predicting overtopping. The application of Machine Learning (ML) algorithms has become increasingly prominent in models for estimating wave overtopping at flood defences. Here we review ML methods as tools for accurate prediction of overtopping and overtopping parameters. A systematic review of 32 publications, published between 2001 and 2021 (last twenty years), underpinned Decision Trees and Artificial Neural Network (ANN) as the most popular ML methods as analysis of wave overtopping datasets. A comparison of estimates of overtopping and overtopping parameters using these models with those from commonly used (empirical) prediction models, highlights the potential of ML methods for these applications. The review, however, highlights important limitations of the methods and identifies future research needs that may serve as an impetus for further development of these ML algorithms for wave overtopping, particularly in applications characterised by complex geometrical configurations.