Fuzzy model forecasting of offshore bar-shape profiles under high waves

This paper proposes a fuzzy model for predicting the complex changes of offshore beach topographies under high waves. The fuzzy model was developed through the integration of autoregressive exogenous input models, a Takagi-Sugeno fuzzy model, subtractive clustering algorithms, and a weighted least squares estimation technique. The height, the period of ocean wave signals, and the initial cross-shore bar shapes are used as input signals while the topographic features of the bar shape profiles are adopted as the output signals. To demonstrate the effectiveness of the proposed fuzzy model, a variety of laboratory experiments at 1/50th scale were conducted and compared to the CSHORE mathematical model. The experimental studies show that the proposed fuzzy model is effective in predicting the topographic features of beach profiles and performs better than the CSHORE model. (C) 2014 Elsevier Ltd. All rights reserved.