Modeling daily suspended sediment load using improved support vector machine model and genetic algorithm.

Prediction of sediment volume and sediment load is always one of the important issues for decision-makers of watershed basins. The present study investigated the daily suspended sediment load in a watershed basin using the improved support vector machine method. Since in most of the previous studies, the coefficients of the support vector machine method had been calculated based on trial and error, in the present study, the combination of the support vector machine and the genetic algorithm is used. In the first step, the unknown parameters of the support vector machine are calculated and then, the sediment load simulation is performed. Two case studies in the present work involve two earth dams in Semnan Province called Veynakeh and Royan. Furthermore, multivariate adaptive regression spline (MARS) and MT tree model (M5T) methods are used for comparison. The results indicated that the input combination of discharge data at the current time and one, two, and three previous days has the best performance for all models. Also, the support vector machine-genetic algorithm (SVM-GA) model has a lower root mean square error (RMSE) and mean absolute error (MAE) compared to the MARS and M5T models for both stations. In addition, comparing observational data with simulation data based on the R2 coefficient suggested that the SVM-GA model offers more accurate results than the other two methods. Accordingly, the SVM-GA method used in this study has a high potential for simulating sediment volume.

Determination of number of check dams by artificial neural networks in arid regions of Iran.

An artificial neural network (ANN) model with six hydrological factors including time of concentration (TC), curve number, slope, imperviousness, area and input discharge as input parameters and number of check dams (NCD) as output parameters was developed and created using GIS and field surveys. The performance of this model was assessed by the coefficient of determination R(2), root mean square error (RMSE), values account and mean absolute error (MAE). The results showed that the computed values of NCD using ANN with a multi-layer perceptron (MLP) model regarding RMSE, MAE, values adjustment factor (VAF), and R(2) (1.75, 1.25, 90.74, and 0.97) for training, (1.34, 0.89, 97.52, and 0.99) for validation and (0.53, 0.8, 98.32, and 0.99) for test stage, respectively, were in close agreement with their respective values in the watershed. Finally, the sensitivity analysis showed that the area, TC and curve number were the most effective parameters in estimating the number of check dams.