摘要：In this study, Local Linear Regression (LLR), Dynamic Local Linear Regression (DLLR), Artificial Neural Networks (ANNs) and Adaptive Neuro Fuzzy Inference System (ANFIS) were employed to estimate total infiltration rate using first and second 5 min time period infiltration rates measured in different kinds of patches (shrub, grass and iris) and interpatch (bare soil) in an arid rangeland ecosystem with 188 mm annual precipitation in Yazd, central part of Iran. Infiltration rates measured using ring method. The performances of these models were assessed using Nash-Sutcliffe model efficiency coefficient (E), Root Mean Square Error (RMSE) and coefficient of determination (R2). According to the results, the ANFIS model shows superiority in the accuracy of estimating total infiltration rate. The results produced by ANN also show a relatively good level of accuracy. In all the cases used in this study, the accuracy of the results produced by these techniques (especially ANFIS) was higher than those produced by the other two linear models (LLR and DLLR).
