R. Rezae Arshad, Gh. Sayyad, *, M. Mazloom, M. Shorafa, A. Jafarnejady,
Volume 16, Issue 60 (7-2012)
Abstract
Direct measurement of soil hydraulic characteristics is costly and time-consuming. Also, the method is partly unreliable due to soil heterogeneity and laboratory errors. Instead, soil hydraulic characteristics can be predicted using readily available data such as soil texture and bulk density using pedotransfer functions (PTFs). Artificial neural networks (ANNs) and statistical regression are two methods which are used to develop PTFs. In this study, the multi-layer perceptron (MLP) neural network and backward and stepwise regression models were used to estimate saturated hydraulic conductivity using some soil characteristics including the percentage of particle size distribution, porosity, and bulk density. Data of 125 soil profiles were collected from the reports of basic soil science and land reclamation studies conducted by Khuzestan Water and Power Organization. The results showed that MLP neural network having Bayesian training algorithm with the greater coefficient of determination (R2=0.65) and the lower error (RMSE =0.04) had better performance than multiple linear regression model in predicting saturated hydraulic conductivity.
K. Roshangar, R. Valizadeh,
Volume 21, Issue 2 (8-2017)
Abstract
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.
