The New EurOtop Neural Network Tool for an Improved Prediction of Wave Overtopping

The goal of this work is to present the Artificial Neural Network (ANN) tool released with the second edition of the wave overtopping manual, EurOtop, 2016. The ANN predicts the main parameters representative of the wave-structure interaction processes, i.e. the mean wave overtopping discharge q, the wave transmission and the wave reflection coefficients Kt and Kr. Such tool provides an improved prediction of q with respect to existing and available similar tools, and includes a correction factor accounting for scale effects in case of rubble mound structures with small overtopping rates. The accuracy of the ANN predictions is characterized by values of the coefficient of determination R2 that are greater than 0.90 for all the outputs. A website and a Graphical User Interface have been developed to make the ANN tool a user-friendly, fast and reliable design instrument available to the coastal engineering community.