Estimation of Wave Breaking Index by Learning Nonlinear Relation using Multilayer Neural Network

Abstract

Estimating wave breaking parameters such as wave height and water depth is essential to understanding the location and scale of the breaking wave. Therefore, numerous wave flume laboratory experiments have been conducted to develop empirical wave breaking formulas. However, the nonlinearity between parameters has not been fully incorporated into the empirical equations. Thus, this study proposes a multilayer neural network utilizing nonlinear activation function and backpropagation to extract nonlinear relationship. Existing laboratory experiment data for the monochromatic regular wave are used to learn the proposed network. Specifically, the bottom slope, deep-water wave height and wave period are plugged in as the input values that simultaneously estimate the breaking wave height and wave breaking location. Typical empirical equations employ deep-water wave height and length as input variables to predict the breaking wave height and water depth. A newly proposed model directly utilizes wave breaking index without nondimensionalization. Thus, applicability can be significantly improved. The estimated wave breaking index is statistically verified using B, RMSE, and R. The performance of the proposed model is better than existing breaking wave index formulas as well as robust to laboratory experiment conditions, such as wave condition, bottom slope, and experimental scale.