Application of multilayer perceptron neural network and support vector machine for modeling the hydrodynamic behavior of permeable breakwaters with porous core

In this research, the application of multilayer perceptron (MLP) neural networks and support vector machine (SVM) for modeling the hydrodynamic behavior of Permeable Breakwaters with Porous Core has been investigated. For this purpose, experimental data have been used on the physical model to relate the reflection and transition coefficients of incident waves as the output parameters to the width of the breakwater chamber, the ratio of the height of rockfill material to the water depth, the ratio of the width of the chamber to the wavelength, Wave number in water depth and wave steepness. The results indicate that the MPL model has better performance in modeling the hydrodynamic behavior than the SVM model and is largely correlated to real data (R = 0.8689 for reflection coefficient and 0.96629 R = for transient coefficient). In order to reveal the response of reflection and transition coefficients to each input parameter, a parametric study was performed. Also, using the sensitivity analysis, the participation rate of each input parameters in the prediction of reflection and transient coefficients has been studied.