Automated detection of offshore wave power using machine learning techniques

Background: Various statistical methods are used for estimating sea state and wave characteristics using digital wave models. Several machine learning techniques help to develop the computational difficulties of these methods.Materials and methods: This study aims to estimate the wave power with Extreme Learning Machine (ELM), Regression, Restricted Boltzmann Machine (RBM), and RBM-ELM methods using nonlinear wave input param-eters at different depths. Furthermore, the performance criteria are improved by applying the Relief feature selection algorithm to these methods. The input bias and input weights for the ELM have been determined using the RBM.Results: In the RBM-based presented method, the highest estimation values were obtained using Relief feature selection and without Relief as 96.96% and 94.02%, respectively. The highest accuracy rate based on ELM is 76.86% in the estimation of wave power without Relief. In the same way, the accuracy rate with Relief was calculated as 92.16%. These values were increased to 90.10% (without Relief) and 95.73% (with Relief) using the RBM-ELM method.Conclusions: This study demonstrates that the performance of the presented methods with Relief feature selection was improved.