Estimation of the Input Height of Irregular Waves Generated at a Wave Maker by Using Gaussian Process Regression and Artificial Neural Networks

A neural network (NN) and Gaussian process regression (GPR) model for predicting the input wave height of the wave generator were established, and their performance was evaluated and compared using irregular wave data acquired in a two-dimensional wave flume. Both models were able to predict the input wave height that can produce the target wave height of irregular waves with a very high accuracy. Among the two models, the GPR model showed better performance than the NN model. Based on the results of this study, it is expected to reduce the time required for experiments by shortening trial and error in setting the input wave height of the wave generator when conducting physical experiments in a wave flume.