Revealing the synergistic spatial effects in soil heavy metal pollution with explainable machine learning models

The identification of factors that affect changes in the heavy metal content of soil is the basis for reducing or preventing soil heavy metal pollution. In this research, 16 environmental factors were selected, and the influences of soil heavy metal spatial distribution factors and the synergy amongst space factors were evaluated using a geographic detector (GD) and the extreme gradient boosting (XGBoost)-Shapley additive explanations (SHAP) model. Three heavy metal elements, namely, Cd, Cu and Pb, in the study region were examined. The following results were obtained. (1) XGBoost demonstrated high accuracy in predicting the spatial distributions of soil heavy metals, with each heavy metal having an R² value of over 0.6. (2) Geological type map (Geomap) and enterprise density considerably affected the concentrations of Cd, Cu and Pb in soil in the GD and XGBoost-SHAP models. In addition, cross-detection revealed strong explanatory power when natural and human factors were combined. (3) Under the same geological background, the different trends of gross domestic product effects on heavy metals indicated that pollution control measures were effective in economically developed areas, and the economy and the environment could be balanced. Meanwhile, the interaction between the normalised difference vegetation index and enterprise density showed that vegetation could alleviate heavy metal pollution in the region. This study supports strategic decision-making, serving as a reference for the global management of soil heavy metal contamination, sustainable ecological development and assurance of people's health and well-being.