Ocean Wave Forecasting Using Recurrent Neural

The tremendous increase in offshore operational activities demands improved waveforecasting techniques. With the knowledge of accurate wave conditions, it is possible to carry out the marine activities such as offshore drilling, naval operations, merchant vessel routing, nearshore construction, etc. more efficiently and safely. This paper describes an artificial neural network, namely recurrent neural network with rprop update algorithm and is applied for wave forecasting. Measured ocean waves off Marmugao, west coast of India are used for this study. Here, the recurrent neural network of 3, 6 and 12 hourly wave forecasting yields the correlation coefficients of 0.95, 0.90 and 0.87 respectively. This shows that the wave forecasting using recurrent neural network yields better results than the previous neural network application. INTRODUCTION Ocean waves can be either forecasted using the meteorological conditions or hindcasted from the existing meteorological charts. However, the forecast may not accurately represent the measured values. The parametric or differential equation based on wind wave relationship and a differential equation of wave energy are solved numerically in wave forecasting. This is generally employed to give an estimate over the following 6-72 hours or so. The spatial wave information on numerical wave forecasting schemes are useful and attractive in many applications, but it needs elaborate meteorological and oceanographic data sets and involves an enormous amount of computational effort. Apart from this translation of data from wind to waves results in an element of uncertainty and approximation of forecasts (Herbich, 1990). The work carried out by Deo and Naidu (1999) describes the application of neural network analysis in forecasting of waves and is carried out for significant wave height (Hs) with 3 hour lead period. They have carried out various combinations of training