Abstarct: Cation exchange capacity (CEC) and heavy mextal pollution are most important soil chemical parameters but they measurement is difficult and need lots of time as well as costs. With respect to the problem of direct measurement of this parameter in recent year using indirect method such as artificial neural networks, ANFIS and other similar models has been considered. In the present study, 250 soil samples were collected from Gulian location in Guilan province. Some soil chemical as well as physical properties such as organic carbon, total nitrogen, soil texture, pH and electrical conductivity (EC) were considered as input laxyer and CEC, pb and Cd as output laxyer. The collected data randomly divided in two categories of training (80%) and testing (20%) and they used for train and test of artificial neural networks, multi-laxyer perception (MLP), ANFIS and nonlinear regression model. Results of this research show high efficiency of artificial neural network compare with nonlinear regression and also MLP network was better than ANFIS network in testing level. Although ANFIS model in train level was better than MLP. Sensitivity analysis was also performed for all parameters to find out the relationship between soil parameters and soil cation exchange capacity and soil Pb and Cd content. At last, the correlation between soil parameters and soil cation exchange capacity and soil Pb and Cd content was determined and most important parameters which could influence the soil cation exchange capacity and soil Pb and Cd content were described; Results Show that organic carbon percentage with cation exchange capacity and soil Pb and Cd content have most correlation.