Forecasting of Time Series Significant Wave Height Using Wavelet Decomposed Neural Network

Abstract In this current study, a hybrid model of wavelet and Artificial Neural Network (WLNN) has been developed to forecast time series significant wave height for lead times up to 48 h. The data used in the hybrid model are significant wave heights (Hs) belongs to two stations, one near to New Mangalore port, Indian ocean and another near to west of Eureka, Canada in North Pacific ocean. The three hourly significant wave height data for a period of one year was first decomposed through discrete wavelet transformation in order to obtain frequencies of different bands in the form of wavelet coefficients. Later these coefficients are used as inputs into Levenberg Marquardt artificial neural network models to forecast time series significant wave heights at multistep lead time. Two different methods WLNN-1 &WLNN-2 employed for the first station data to forecast significant wave heights at higher lead times. From the result it is found that the second method (WLNN-2) in wavelet-ANN model performed better than first method (WLNN-1).Model results obtained for two stations showed good predictions at lower lead times but slight deviation observed at higher lead times. As compared to first station results, the second station results are slightly poor because of more statistical variations in the data set.