JWSS - Journal of Water and Soil Science

Hydraulic jump is the most common method of dissipating water’s kinetic energy in downstream of spillways, shoots and valve. In this paper, Support Vector Machine (SVM) method, as a machine learning method, have been used to estimate hydraulic characteristics such as the sequent depth ratio, jump length and energy loss in three different sudden expansions stilling basins, and the rate of influence of input parameters in each jump has been analyzed. In order to evaluate the performance of proposed method, 936 sets of the observed data have been used for training and testing process of three kinds of expanding channel models. Furthermore, a comparison between semi-theoretical approaches and the data obtained from the best SVM models have been carried out. The results confirmed the efficiency of SVM method for estimating the hydraulic jump characteristics and proved that this method performed well in comparison to the semi-theoretical relationships. The obtained results revealed that the superior model for the sequent depth ratio and relative energy dissipation was the model with (Fr₁,h₁/B) parameters and the superior model for the length of hydraulic jump prediction was the model with (Fr₁, h₂/h₁) parameters.