With respect to the problem of direct measurement of soil parameters in recent year using indirect method such as artificial neural networks has been considered. In the present study, 200 soil samples were collected from Ghoshe location in Semnan province. Half of samples were collected from disturbed agricultural lands and the other half were collected from undisturbed nearby lands. Some soil chemical as well as physical properties such as electrical conductivity (EC), soil texture, lime percentage, sodium adsorption ration (SAR) and bulk density were considered as easy and fast obtainable features and soil cation exchange capacity as difficult and time consuming feature. The collected data randomly divided in two categories of training (70%) and testing (30%) and they used for train and test of two artificial neural networks, multi-layer perception using back-propagation algorithm (MLP/BP) and Radial basis functions (RBF) and nonlinear regression model. Results of this research show high efficiency of artificial neural network compared with nonlinear regression and also MLP network was better than RBF network. Sensitivity analysis was also performed for all parameters to find out the relationship between soil mentioned parameters and soil cation exchange capacity for both disturbed and undisturbed soils. At last, the correlation between soil parameters and soil cation exchange capacity was determined and most important parameters which could influence the soil cation exchange capacity were described.