Selenium and Cadmium Behaviour in Karst Rock–Soil–Crop Systems: Spatial Machine-Learning Evidence for Land-Quality Monitoring

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.