A Machine Learning Model for Wave Prediction Based on Support Vector Machine

In this paper, we propose a least square support vector machine (LSSVM) model to predict ocean wave elevations in a random sea state. The frequency and time domain characteristics of historical wave data were both considered in the proposed model. The wave data following a JONSWAP (Joint North Sea Wave Project) spectrum measured through an indoor wave tank experiment were used for the study. The measured time series were transformed to the frequency domain by the fast Fourier transform and divided into five bands by a filtering method. With the time series corresponding to each band, the LSSVM model was trained separately and used to predict future time series. The proposed model is shown to greatly extend the prediction time length, making it more effective for the application of short-term real-time wave prediction. Both wave elevations and wave forces were studied as applications of the model.