Prediction Characteristics of Free and Submerged Hydraulic Jumps on Horizontal and Sloping Beds using SVM Method

Abstract Doubtlessly hydraulic jump is a useful phenomenon in open channel flow such as rivers and spillways. As the most important characteristics of hydraulic jump, length, and sequent depth ratio play a key role in designing of hydraulic structures. The hydraulic jump length is one of the most im...
Ausführliche Beschreibung

Abstract Doubtlessly hydraulic jump is a useful phenomenon in open channel flow such as rivers and spillways. As the most important characteristics of hydraulic jump, length, and sequent depth ratio play a key role in designing of hydraulic structures. The hydraulic jump length is one of the most important parameters, which cannot be calculated by mathematical analyses directly. In this context, several relations have been proposed to estimate the length and sequent depth ratio of the hydraulic jumps, but the results of the mentioned equations are not general and acceptable due to the uncertainty of the functions. Achievements of this study follows three aims; firstly to develop and examine support vector machine (SVM) for estimating characteristics of five types of free and submerged hydraulic jumps; secondly to compare the results of SVM models with analytical and semi-empirical equations; and finally to perform a sensitivity analysis to investigate the effect of each input parameter on the output in terms of root mean square error (RMSE), correlation coefficient (R) and Nash-Sutcliffe or determination coefficient (NS or DC). The meteorological data sets used herein to develop the models are obtained from previous credible researches. Performance of the models appoints dominant parameters for predicting the characteristics of the different types of hydraulic jumps As Also based on the comparisons among the SVM models, analytical and semi-empirical equations, it can be seen that, SVM models depict better results than those equations. Ausführliche Beschreibung