Fuzzy clustering analysis for modeling of soil cation exchange capacity

The objective of this study was to investigate fuzzy clustering analysis based on subtractive clustering algorithm for modeling of Soil Cation Exchange Capacity (CEC). In this work, seventy soil samples were collected from different horizons of 15 soil profiles located in the Ziaran region, Qazvin province, Iran. The data set was divided into two subsets. One for calibration (80% data) and second for testing the models (20% data). The performance of the subtractive clustering algorithm was evaluated using an independent test data set. The vector options, i.e. (i) range of influence, (ii) squash factor, (iii) accept ratio and (iv) reject ratio were used for specifying clustering algorithm parameters to override the default values. The analyses considered 0.5, 1.25, 0.5 and 0.15 values for mentioned parameters, respectively. In order to evaluate the model, root mean square error (RMSE) and coefficient of determination (R) were used. The corresponding values for fuzzy subtractive clustering algorithm were 0.1751 and 0.9931, respectively. Results showed that fuzzy subtractive clustering algorithm had high accuracy in predicting and modeling of soil cation exchange capacity.