TY - JOUR
T1 - Predicting the governing factors for the release of colloidal phosphorus using machine learning
AU - Khan, Sangar
AU - Gao, Huimin
AU - Milham, Paul
AU - Eltohamy, Kamel Mohamed
AU - Ullah, Habib
AU - Mu, Hongli
AU - Gao, Meixiang
AU - Yang, Xiaodong
AU - Hamid, Yasir
AU - Hooda, Peter S.
AU - Shaheen, Sabry M.
AU - Wu, Naicheng
N1 - Publisher Copyright:
© 2024 Elsevier Ltd
PY - 2024/8
Y1 - 2024/8
N2 - Predicting the parameters that influence colloidal phosphorus (CP) release from soils under different land uses is critical for managing the impact on water quality. Traditional modeling approaches, such as linear regression, may fail to represent the intricate relationships that exist between soil qualities and environmental influences. Therefore, in this study, we investigated the major determinants of CP release from different land use/types such as farmland, desert, forest soils, and rivers. The study utilizes the structural equation model (SEM), multiple linear regression (MLR), and three machine learning (ML) models (Random Forest (RF), Support Vector Regression (SVR), and eXtreme Gradient Boosting (XGBoost)) to predict the release of CP from different soils by using soil iron (Fe), aluminum (Al), calcium (Ca), pH, total organic carbon (TOC) and precipitation as independent variables. Results show that colloidal-cations (Fe, Al, Ca) and colloidal-TOC strongly influence CP release, while bioclimatic variables (precipitation) and pH have weaker effects. XGBoost outperforms the other models with an R2 of 0.94 and RMSE of 0.09. SHapley Additive Explanations described the outcomes since XGBoost is accurate. The relative relevance ranking indicated that colloidal TOC had the highest ranking in predicting CP. This was supported by the analysis of partial dependence plots, which showed that an increase in colloidal TOC increased soil CP release. According to our research, the SHAP XGBoost model provides significant information that can help determine the variables that considerably influence CP contents as compared to RF, SVM, and MLR.
AB - Predicting the parameters that influence colloidal phosphorus (CP) release from soils under different land uses is critical for managing the impact on water quality. Traditional modeling approaches, such as linear regression, may fail to represent the intricate relationships that exist between soil qualities and environmental influences. Therefore, in this study, we investigated the major determinants of CP release from different land use/types such as farmland, desert, forest soils, and rivers. The study utilizes the structural equation model (SEM), multiple linear regression (MLR), and three machine learning (ML) models (Random Forest (RF), Support Vector Regression (SVR), and eXtreme Gradient Boosting (XGBoost)) to predict the release of CP from different soils by using soil iron (Fe), aluminum (Al), calcium (Ca), pH, total organic carbon (TOC) and precipitation as independent variables. Results show that colloidal-cations (Fe, Al, Ca) and colloidal-TOC strongly influence CP release, while bioclimatic variables (precipitation) and pH have weaker effects. XGBoost outperforms the other models with an R2 of 0.94 and RMSE of 0.09. SHapley Additive Explanations described the outcomes since XGBoost is accurate. The relative relevance ranking indicated that colloidal TOC had the highest ranking in predicting CP. This was supported by the analysis of partial dependence plots, which showed that an increase in colloidal TOC increased soil CP release. According to our research, the SHAP XGBoost model provides significant information that can help determine the variables that considerably influence CP contents as compared to RF, SVM, and MLR.
KW - Artificial intelligence
KW - Eutrophication
KW - Land use types
KW - Nutrients management
KW - Phosphorus loss
UR - http://www.scopus.com/inward/record.url?scp=85197396888&partnerID=8YFLogxK
U2 - 10.1016/j.chemosphere.2024.142699
DO - 10.1016/j.chemosphere.2024.142699
M3 - Article
C2 - 38944354
AN - SCOPUS:85197396888
SN - 0045-6535
VL - 362
JO - Chemosphere
JF - Chemosphere
M1 - 142699
ER -