Source apportionment and the elucidation of driving mechanisms are essential for targeted soil pollution management. This study investigated surface soils across six towns in southern Shimen County, northwestern Hunan Province, where 662 samples were collected to determine the concentrations of As, Cd, Cr, Cu, Ni, Pb, and Zn. Multivariate statistics and the APCS-MLR receptor model were integrated to quantify pollution sources, while three machine learning models (RF, XGBoost, and LightGBM) were applied to identify key drivers of the spatial enrichment of Cd. Results showed that Cd was significantly enriched, with a mean concentration of 0.43 mg/kg (3.41 times the provincial background value). The mean concentrations of As, Cr, Cu, Ni, Pb and Zn were 11.97 mg/kg, 81.01 mg/kg, 24.15 mg/kg, 49.25 mg/kg, 29.56 mg/kg and 76.77 mg/kg, respectively, and these PTEs remained at normal background levels. Significant inter-element correlations indicated common sources. Three primary sources were quantified—natural parent material (43.83%), mining activities (30.99%), and mixed sources of coal mining and agricultural inputs (7.84%), with 17.34% attributed to unidentified mixed sources. Natural sources dominated the geogenic enrichment of Cd, Cu, Ni, Pb, and Zn; mining activities governed the accumulation of As, Cr, Cu, and Pb; a mixed source of coal mining and agricultural practices contributed substantially to Cd enrichment. Machine learning identified PM10, topography, strata, and soil type as dominant drivers, with their total feature importance reaching 70.05%. Among these factors, natural factors and anthropogenic factors accounted for 44.23% and 55.77% of the total feature importance, in turn revealing coupled natural–anthropogenic controls. This study establishes an integrated framework linking source apportionment and driver identification, providing scientific insights for potentially toxic elements (PTEs) control in analogous mining–agricultural regions.
Wang et al. (Wed,) studied this question.