Modeling Average Grain Velocity for Rectangular Channel Using Soft Computing Techniques

This study was undertaken with the primary objective of modeling grain velocity based on experimental data obtained under controlled conditions a laboratory using rectangular hydraulic tilting channel. Soft computing approaches, i.e., support vector machine (SVM), artificial neural network (ANN), and multiple linear regression (MLR), were applied to simulate four input variables; shear velocity, exposed area base ratio (EATBAR), relative depth, sediment particle weight. Quantitative performance evaluation predicted values performed help three different standard statistical indices, such as root mean square error (RMSE), Pearson’s correlation coefficient (PCC), Wilmot index (WI). The results during testing phase revealed that SVM model has RMSE (m/s), PCC, WI 0.1195, 0.8877, 0.7243, respectively, providing more accurate predictions than MLR ANN models phase.