Neural Network Calibration Method For Varans Models To Analyse Wave-Porous Structures Interaction

Abstract

This study develops a calibration method for the porous media to properly model the interaction between waves and coastal structures using VARANS models. The proposed method estimates the porosity, n_p, and the optimum values of the Forchheimer coefficients,  and . Physical tests were conducted in a 2D wave flume for a homogeneous mound breakwater. Numerical tests were carried out using the IH-2VOF model to simulate the corresponding physical tests and incident wave conditions (H_I, T). The numerical tests covered a wide range of Forchheimer coefficients found in the literature,  and , and the porosity, n_p, with a total of 555 numerical tests. The results of 375 numerical tests using IH-2VOF were used to train a Neural Network (NN) model with five input variables (H_I, T, n_p,  and ) and one output variable . The NN model explained more than 90% (R² > 0.90) of the variance of the squared coefficient of reflection, . This NN model was used to estimate the  in a wide range of n_p,  and , and the error () between the physical measurements and the NN estimations of was calculated. The results of  as function of n_p,  and  showed that for a given porosity, n_p, it was difficult to obtain a pair of  and  values that gave a common low error if few physical tests are used for calibration. The minimum root-mean-square error of  ( was calculated to find the optimum values of porosity and Forchheimer coefficients: n_p = 0.44,  = 200 and  = 2.825 for the tested structure. Blind tests were conducted with the remaining 180 numerical tests using IH-2VOF to validate the proposed method for VARANS models.