Heavy metal pollution in surface soils poses significant environmental and health risks, yet the factors driving its spatial distribution remain poorly understood in certain regions. This study investigates the distribution and key influencing factors of heavy metal contamination in surface soils across Zhenjiang and Yangzhou, Jiangsu Province, China. This study analyzed the chemical compositions of 449 soil samples from the study area. Descriptive statistics, stepwise multiple regression, and the random forest (RF) method were employed to identify the key factors affecting the distribution and migration of heavy metals in soils. According to the national standards for soil risk screening values, cadmium (Cd) and mercury (Hg) were identified as the most heavily contaminated heavy metals in the study area. The average concentrations of Cd and Hg were 2.38 and 2.32 times higher than the provincial soil background values, respectively. A substantial proportion of samples exceeded the risk screening thresholds established for agricultural land. Key factors influencing the distribution of heavy metals in surface soils include soil iron oxides, pH, total organic carbon (Corg.), cation exchange capacity (CEC), and weathering intensity, as represented by the Chemical Index of Alteration (CIA). By integrating advanced data analysis techniques, this study provides new insights into the mechanisms governing heavy metal pollution in soils, offering a foundation for targeted soil management and pollution mitigation strategies.

Selenium (Se) and cadmium (Cd) have contrasting implications for agricultural land quality. We integrated 25 unpaired rock samples and 149 soil records, including 106 paired soil–crop observations from Zhijin County, Guizhou, China, to characterise element distributions and evaluate static predictive models under spatially blocked cross-validation. Crop Se values below detection were treated as LOD/√2; models used 88 numerical Se records and 106 Cd records across five spatial KMeans blocks. Rock, soil and crop data showed element-specific concentration patterns, bioconcentration factors and soil associations. The highest pooled out-of-fold performance was obtained for Crop Se (R² = 0.831, RMSE = 0.220 log10 mg kg⁻¹), whereas Crop Cd showed weaker performance (R² = 0.233, RMSE = 0.495 log10 mg kg⁻¹). Crop Se robustness analyses showed sensitivity to censoring treatment and crop-group structure, and fold-contained within-crop residual prediction was weak (R² = 0.007). Fitted associations involved soil Se, soil Cd, pH, MgO, organic C and crop group, conditional on correlated environmental and management factors. These findings support crop-stratified sampling across representative geological and soil settings for Se monitoring, while Cd surveillance remains centred on direct crop measurement. The models provide a transparent basis for sampling design and targeted field verification.