Hindcasting of wave parameters using different soft computing methods

Hindcasting of wave parameters is necessary for many applications in coastal and offshore engineering and is generally made with the help of sophisticated numerical models. This paper presents alternative hindcast models based on Artificial Neural Networks (ANNs), Fuzzy Inference System (FIS) and Adaptive-Network-based Fuzzy Inference System (ANFIS). The data set used in this study comprises wave and wind data gathered from deep water location in Lake Ontario. Wind speed, wind direction, fetch length and wind duration were used as input variables, while significant wave height, peak spectral period and mean wave direction were the output parameters. Different topologies of ANNs were considered to predict the wave parameters and the relative importance of input parameters were determined. Finally, the results of ANNs-based models, FIS- and ANFIS-based models were compared. Results indicated that error statistics of soft computing models were similar, while ANFIS models were marginally more accurate than FIS and ANNs models.