Estimation of steady infilterability rate using Neuro-Fuzzy, Artificial neural network and Multivariate linear regression models

Infiltration is the most important soil physical characteristic which its direct measurement is laborious, time consuming and expensive. The purpose of this study is to estimate steady infilterability rate, using Neuro-Fuzzy, Neural Network and Multivariate Linear Regression models. Consequently, steady infilterability rate, was measured using double rings in 100 points in Dehgolan region, Kurdistan Province, Iran. Soil physical (porosity, bulk density, sand, silt and clay) and topography characteristics were measured as readily available properties and used to estimate steady infilterability rate, The data were divided into two sets of terrain (70% of the data) and test (30% of the data). The models based on input type were categorized into type 1 (physical characteristics) and 2 (soil physical and topography characteristics). The results based on mean bias error (MBE), Root Mean Square Error (RMSE), Mean Error (ME), Relative Standard Error (RSE) and Relative Improvement (RI) showed that the Neuro-Fuzzy model (type 1 respectively with statistics 0.24, 2.01, 0.46, 4.04 and 46.65) (type 2 respectively with statistics -0.1, 1.24, 0.23, 1.54 and 58.62) has the most accuracy of steady infilterability rate, estimation. Also was observed using topography data as input together with soil physical characteristics can lead to improvement of the estimation accuracy of steady infilterability rate.