Forecasting of Significant Wave Height using Support Vector Regression

The reliability of wave prediction is a crucial issue in coastal, harbor and ocean engineering. Support vector machine (SVM) is an appropriate and suitable method for significant wave height (H-s) prediction due to its best versatility, robustness, and effectiveness. In this present work, only significant wave height (H-s) of previous time steps were used as predictors during the period 01-01-2004 to 01-04-2004. The data used is processed significant wave height (H-s) of the station SW4(Latitude 12056'31 '' and longitude 74043'58 '') located near west coast of India. 70% of the data used for calibration of model parameters and remaining 30% data used for validation using various input combinations. The performance of both the RBF and PUK models is assessed using different statistical indices. (E.g. CC (RBF-SVR) = 0.82, CC (PUK-SVR) = 0.93; MAE (RBF-SVR) = 0.04, MAE (PUK-SVR) = 0.04 RMSE (RBF-SVR) = 0.06, RMSE (PUK-SVR) = 0.05. The results show that SVM can be successfully used for prediction of Hs.