The interaction of wheel and soil has received much attention from the researchers of this department due to its effects on energy consumption and soil characteristics, especially in the field of agriculture. In this research, the amount of wheel indentation in the soil and the traction force required by the moving wheel, which are the determining parameters in the wheel-soil interaction, were measured using a wheel tester in the laboratory soil storage environment. Tests in 2 different levels of speed (0.386 and 0.879 km/hour), 3 different levels of tire pressure (18, 25 and 32 pounds per square inch) and 3 different levels of load Vertical loading on wheels (150, 300 and 450 kg) was carried out in the form of a randomized complete block design in 3 repetitions and a total of 54 surveys. Then, using adaptive neuro-fuzzy inference system (Anfis) and multivariable regression model, the amount of indentation and required tensile force were predicted. In order to evaluate these models, correlation coefficient (R2) and mean square error (MSE) were used. The results showed that tire air pressure, vertical force and moving speed of the moving wheel have a significant effect on the depth of the wheel indentation in the soil (P<0.01). They do not have correlation coefficient in predicting the amount of indentation and tensile force by Enfis models was equal to 0.9901 and 0.6911, respectively, which was much higher than the correlation coefficient in regression models, which was equal to 0.8743 and 0.4061, respectively. Also, the mean square error in Enfis models regarding the indentation and traction force of the wheel is 0.0231 and 0.0101, respectively, which is much lower than the mean square error in the regression models, which is equivalent to 0.864 and 0.918, respectively. Be Therefore, Anfis models have higher accuracy and less error than regression models.