JWSS - Journal of Water and Soil Science

---

Soil fertility measures such as cation exchange capacity (CEC) may be used in upgrading soil maps and improving their quality. Direct measurement of CEC is costly and laborious. Indirect estimation of CEC via pedotransfer functions, therefore, may be appropriate and effective. Several delineations of two consociation map units consisting of two soil families, Shahrak series and Chaharmahal series, located in Shahrekord plain were identified. Soil samples were taken from two depths of 0-20 and 30-50 cm and were analyzed for several physico-chemical properties. Clay and organic matter percentages as well as moisture content at -1500 kPa correlated best with CEC. Pedotransfer functions were successfully developed using regression and artificial neural networks. In this research, it seemed that one hidden layer with one node was sufficient for all neural networks models. The best regression model consisting of organic matter and clay variables showed R2=0.81 and RMSE=7.2 while best corresponding neural network with a learning coefficient of 0.3 and an epoch of 40 had R2=0.88 and RMSE=0.34. Data partitioning according to soil series and soil depths increased the accuracy and precision of the functions. Compared to regression, artificial neural network technique gave pedotransfer functions with greater R2 and smaller RMSE.

---

CEC of the soil is the exchange sites of organic and inorganic soil colloids. Modeling and Estimation of CEC is a useful indicator for fertility. The new alternative approaches for estimating CEC are indirect methods based on intelligent models. In this research in order to estimate CEC, 485 soil samples were prepared from two regions, chaparsar (Mazandaran in northern Iran) and Bostanabad (North of West Azarbaijan, Iran).In this paper introduces the application of genetic programming. Input parameters that are percent Clay, Organic Carbon and Silt, evaluate using genetic programming, neural network and Neural Inference Systems-Fuzzy models. The results indicate a good ability to intelligent models for CEC Estimation According to indices used in this study. Genetic programming model with a root mean square error of 1.78 and coefficient of determination 0.95 compared to other models have been more efficient and is able to provide satisfactory results, Also are the explicit solutions that reflect the relationship between input an output variable, was presented based on genetic programming. This preferred the genetic programming model adds the other models. Stepwise regression analysis to determine the contribution of each of the parameters indicated in the CEC that organic materials having Most coefficient of variation of 84% is justified CEC and clay and silt, respectively, with a correlation coefficient of 10% and 6% respectively.