Penetration resistance (PR) is an important property of soils, and can be expressed as cone index (CI). Because of high variability, there are no accurate and representative PR data in most cases. Variable PR is considerably affected by gravimetric soil water content (GWC) and bulk density (BD). In this study, artificial neural networks (ANNs) were used to simulate relationship between BD, GWC, and CI. A data set of 381 samples was collected from 2 study sites, Hamadan and Maragheh. Pedotransfer functions (PTFs) were developed using ANNs and linear and nonlinear regression models to predict CI for the combined data set and each data set separately. For the combined and Hamadan data sets, ANNs produced a greater correlation coefficient (R = 0.85) and lower root mean square error (RMSE) compared with the linear regression model (R = 0.70). For the Maragheh data set, however, the regression model yielded better results. Introducing TP and relative saturation (Qv/TP) into the models improved the prediction of CI. The results further showed that ANN models performed better than nonlinear regression models. Therefore, ANNs were recognized as powerful tools to predict CI by BD, GWC, TP, and Qv/TP as the independent variables under the very diverse conditions of the soils and treatments employed.

Penetration resistance (PR) is an important property of soils, and can be expressed as cone index (CI). Because of high variability, there are no accurate and representative PR data in most cases. Variable PR is considerably affected by gravimetric soil water content (GWC) and bulk density (BD). In this study, artificial neural networks (ANNs) were used to simulate relationship between BD, GWC, and CI. A data set of 381 samples was collected from 2 study sites, Hamadan and Maragheh. Pedotransfer functions (PTFs) were developed using ANNs and linear and nonlinear regression models to predict CI for the combined data set and each data set separately. For the combined and Hamadan data sets, ANNs produced a greater correlation coefficient (R = 0.85) and lower root mean square error (RMSE) compared with the linear regression model (R = 0.70). For the Maragheh data set, however, the regression model yielded better results. Introducing TP and relative saturation (Qv/TP) into the models improved the prediction of CI. The results further showed that ANN models performed better than nonlinear regression models. Therefore, ANNs were recognized as powerful tools to predict CI by BD, GWC, TP, and Qv/TP as the independent variables under the very diverse conditions of the soils and treatments employed.