Improving Significant Wave Height Prediction Using a Neuro-Fuzzy Approach and Marine Predators Algorithm

This study investigates the ability of a new hybrid neuro-fuzzy model by combining (ANFIS) approach with marine predators’ algorithm (MPA) in predicting short-term (from 1 h ahead to day ahead) significant wave heights. Data from two stations, Cairns and Palm Beach buoy, were used assessing considered methods. The ANFIS-MPA was compared other methods, ANFIS genetic (ANFIS-GA) particle swarm optimization (ANFIS-PSO), height for multiple lead times ranging day. multivariate adaptive regression spline investigated deciding best input prediction models. generally offered better accuracy than models both stations. It improved ANFIS-PSO ANFIS-GA 8.3% 11.2% root mean square errors time test period.