Estimation of Cation Exchange Capacity for Low-Activity Clay Soil Fractions Using Experimental Data from South China
The cation exchange capacity (CEC) of the clay fraction (<2 μm), denoted as CEC<sub>clay</sub>, serves as a crucial indicator for identifying low-activity clay (LAC) soils and is an essential criterion in soil classification. Traditional methods of estimating CEC<sub>clay</su...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/14/11/2671 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850149530259947520 |
|---|---|
| author | Jun Zhu Zhong-Xiu Sun |
| author_facet | Jun Zhu Zhong-Xiu Sun |
| author_sort | Jun Zhu |
| collection | DOAJ |
| description | The cation exchange capacity (CEC) of the clay fraction (<2 μm), denoted as CEC<sub>clay</sub>, serves as a crucial indicator for identifying low-activity clay (LAC) soils and is an essential criterion in soil classification. Traditional methods of estimating CEC<sub>clay</sub>, such as dividing the whole-soil CEC (CEC<sub>soil</sub>) by the clay content, can be problematic due to biases introduced by soil organic matter and different types of clay minerals. To address this issue, we introduced a soil pedotransfer functions (PTFs) approach to predict CEC<sub>clay</sub> from CEC<sub>soil</sub> using experimental soil data. We conducted a study on 122 pedons in South China, focusing on highly weathered and strongly leached soils. Samples from the B horizon were used, and eight models and PTFs (four machine learning methods, multiple linear regression (MLR) and three PTFs from publication) were evaluated for their predictive performance. Four covariate datasets were combined based on available soil data and environmental variables and various parameters for machine learning techniques including an artificial neural network, a deep belief network, support vector regression and random forest were optimized. The results, based on 10-fold cross-validation, showed that the simple division of CEC<sub>soil</sub> by clay content led to significant overestimation of CEC<sub>clay</sub>, with a mean error of 14.42 cmol(+) kg<sup>−1</sup>. MLR produced the most accurate predictions, with an R<sup>2</sup> of 0.63–0.71 and root mean squared errors (RMSE) of 3.21–3.64 cmol(+) kg<sup>−1</sup>. The incorporation of environmental variables improved the accuracy by 2–10%. A linear model was fitted to enhance the current calculation method, resulting in the equation: <i>CEC<sub>clay</sub></i> = 15.31 + 15.90 × (<i>CEC<sub>soil</sub></i>/<i>Clay</i>), with an R<sup>2</sup> of 0.41 and RMSE of 4.48 cmol(+) kg<sup>−1</sup>. Therefore, given limited soil data, the MLR PTFs with explicit equations were recommended for predicting the CEC<sub>clay</sub> of B horizons in humid subtropical regions. |
| format | Article |
| id | doaj-art-823a0b6dca454d2f96ab48ee780ae78f |
| institution | OA Journals |
| issn | 2073-4395 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj-art-823a0b6dca454d2f96ab48ee780ae78f2025-08-20T02:26:52ZengMDPI AGAgronomy2073-43952024-11-011411267110.3390/agronomy14112671Estimation of Cation Exchange Capacity for Low-Activity Clay Soil Fractions Using Experimental Data from South ChinaJun Zhu0Zhong-Xiu Sun1School of Computer and Software, Nanjing Vocational University of Industry Technology, Nanjing 210023, ChinaCollege of Land and Environment, Shenyang Agricultural University, Shenyang 110866, ChinaThe cation exchange capacity (CEC) of the clay fraction (<2 μm), denoted as CEC<sub>clay</sub>, serves as a crucial indicator for identifying low-activity clay (LAC) soils and is an essential criterion in soil classification. Traditional methods of estimating CEC<sub>clay</sub>, such as dividing the whole-soil CEC (CEC<sub>soil</sub>) by the clay content, can be problematic due to biases introduced by soil organic matter and different types of clay minerals. To address this issue, we introduced a soil pedotransfer functions (PTFs) approach to predict CEC<sub>clay</sub> from CEC<sub>soil</sub> using experimental soil data. We conducted a study on 122 pedons in South China, focusing on highly weathered and strongly leached soils. Samples from the B horizon were used, and eight models and PTFs (four machine learning methods, multiple linear regression (MLR) and three PTFs from publication) were evaluated for their predictive performance. Four covariate datasets were combined based on available soil data and environmental variables and various parameters for machine learning techniques including an artificial neural network, a deep belief network, support vector regression and random forest were optimized. The results, based on 10-fold cross-validation, showed that the simple division of CEC<sub>soil</sub> by clay content led to significant overestimation of CEC<sub>clay</sub>, with a mean error of 14.42 cmol(+) kg<sup>−1</sup>. MLR produced the most accurate predictions, with an R<sup>2</sup> of 0.63–0.71 and root mean squared errors (RMSE) of 3.21–3.64 cmol(+) kg<sup>−1</sup>. The incorporation of environmental variables improved the accuracy by 2–10%. A linear model was fitted to enhance the current calculation method, resulting in the equation: <i>CEC<sub>clay</sub></i> = 15.31 + 15.90 × (<i>CEC<sub>soil</sub></i>/<i>Clay</i>), with an R<sup>2</sup> of 0.41 and RMSE of 4.48 cmol(+) kg<sup>−1</sup>. Therefore, given limited soil data, the MLR PTFs with explicit equations were recommended for predicting the CEC<sub>clay</sub> of B horizons in humid subtropical regions.https://www.mdpi.com/2073-4395/14/11/2671pedotransfer functionmodeling techniquesmachine learningmultiple linear regressiondeep learning |
| spellingShingle | Jun Zhu Zhong-Xiu Sun Estimation of Cation Exchange Capacity for Low-Activity Clay Soil Fractions Using Experimental Data from South China Agronomy pedotransfer function modeling techniques machine learning multiple linear regression deep learning |
| title | Estimation of Cation Exchange Capacity for Low-Activity Clay Soil Fractions Using Experimental Data from South China |
| title_full | Estimation of Cation Exchange Capacity for Low-Activity Clay Soil Fractions Using Experimental Data from South China |
| title_fullStr | Estimation of Cation Exchange Capacity for Low-Activity Clay Soil Fractions Using Experimental Data from South China |
| title_full_unstemmed | Estimation of Cation Exchange Capacity for Low-Activity Clay Soil Fractions Using Experimental Data from South China |
| title_short | Estimation of Cation Exchange Capacity for Low-Activity Clay Soil Fractions Using Experimental Data from South China |
| title_sort | estimation of cation exchange capacity for low activity clay soil fractions using experimental data from south china |
| topic | pedotransfer function modeling techniques machine learning multiple linear regression deep learning |
| url | https://www.mdpi.com/2073-4395/14/11/2671 |
| work_keys_str_mv | AT junzhu estimationofcationexchangecapacityforlowactivityclaysoilfractionsusingexperimentaldatafromsouthchina AT zhongxiusun estimationofcationexchangecapacityforlowactivityclaysoilfractionsusingexperimentaldatafromsouthchina |