Real-time wave forecasting using genetic programming

The forecasting of ocean waves on real-time or online basi is necessary while carrying out any operational activity in the ocean. In order to obtain forecasts that are station-specific a time-seriesbased approach like stochastic modeling or artificial new il network was attempted by some investigators in the past. This paper presents an application ( f a relatively new soft computing too[ called genetic programming for this purpose. Genetic programn ing is an extension of genetic algorithm and it is suited to explore dependency between input and ( utput data sets. The wave rider buoy measurements available at two locations in the Gulfof Mexico i re analyzed. The forecasts ofsignificant wave heights are made over lead times of 3, 6,12 and 24 h. Th( sample size belonged to a period of 15 years and it included an extensive testing period of 5 years. ' 'he forecasts made by the approach of genetic programming indicated that it can be regarded as a p onnising too[ for future applications to ocean predictions. (c) 2008 Elsevier Ltd. All rights reserved.