Modelling the cross-shore profiles of sand beaches using artificial neural networks

Abstract

Artificial neural networks (ANN) have been widely used successfully to solve coastal engineering problems. In this article, they are used to model the cross-shore profile of sandy beaches taking into account the possible effect of marine vegetation (Posidonia oceanica). Sixty ANNs were generated by modifying both the inputs and the number of neurons in the hidden layer. The best results were obtained with the following inputs: wave height perpendicular to the coast and the associated period and probability of occurrence, median sediment size, profile slope, and energy reduction factor due to P. oceanica. With these inputs and 10 neurons in the hidden layer, a mean absolute error of 0.22 m during training and 0.21 m during the test was obtained, which represents an improvement of 81.2% and 55.5% compared to models without and with P. oceanica.