Modeling the infiltration process with soft computing techniques

Abstract

Knowledge of infiltration process is very helpful in designing and planning of irrigation networks. In this study, the Artificial Neural Network (ANN) technique was used to estimate the infiltration rate of the soil. The performance of ANN was equated with other types of artificial intelligence techniques such as Gaussian process (GP), gene expression Programming (GEP), and generalized neural network (GRNN). While a GP, GRNN, and GEP model gives a good estimation performance, the ANN model outperforms them. For this study, a data-set containing 155 observations of the field was analyzed. Out of 155, a sum of 105 data was selected for preparing different algorithms, whereas rest 50 data were selected to test the models. The best ANN model was generated with a single hidden layer with 9 neurons, momentum = 0.2, learning rate = 0.1, and iteration = 1500, respectively. The ANN achieved a coefficient of correlation (CC) equal to 0.9816 and 0.9133 for the preparing and testing data, respectively. Sensitivity analysis concludes that the parameter time is the most effective parameter for the estimation of infiltration rate.