Document Type : Research Paper
Authors
1
Department of Soil Science, Faculty of Agriculture, Bu Ali Sina University, Hamadan, IRAN
2
Department of Soil Science, Faculty of Agriculture, Bu Ali Sina University, Hamadan,, IRAN
3
Ph. D. Student, Soil Science Department, Faculty of Agricultural Sciences, University of Guilan, RASHT, IRAN
Abstract
Abstract
Introduction
Results and Discussion
The correlation between the cation exchange capacity of soil and clay, apparent specific gravity, the ratio of silt to positive sand, calcium carbonate, total exchangeable base cations, and soil reaction was found to be significant at the 1% level. When comparing the RMSE and RI statistics in two sets of training and test data for the entire dataset and for classes separated based on soil texture groups, it was observed that data separation improved the mean in estimating the cation exchange capacity of the soil. Two methods, linear regression and artificial neural networks, were used to estimate the cation exchange capacity. The results showed that for all coarse, medium, and fine texture groups, the artificial neural network test section had a relative improvement coefficient of 87%, while linear regression had a value of 17%. The grouping of data generally increased the estimation ability of the models. Among the groups studied in this research, the texture group showed higher accuracy in predicting cation exchange capacity compared to other groups. Overall, using functions obtained through grouping proved to be an easy and cost-effective method for estimating cation exchange capacity.
Keywords
Main Subjects
)