Groundwater vulnerability assessment is crucial for sustainable water resources management and pollution prevention. Taking Luyi County, Henan Province, China, as the study area, this study applies three supervised machine learning algorithms—Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM)—to establish classification models using nitrate nitrogen (NO₃–N) concentrations above 10 mg/L as the target variable. The predicted probability of contamination is adopted as an indicator of groundwater vulnerability. Model performance was comprehensively assessed using multiple evaluation metrics. The results show that all three models exhibited stable and strong predictive performance, with Area Under the Curve (AUC) values ranging from 0.91 to 0.94 and accuracy exceeding 86.5%. Pearson and Spearman correlation analyses were performed between observed NO₃–N concentrations from 77 monitoring wells and the groundwater vulnerability results, indicating overall better performance than the traditional index-overlay method. Feature importance analysis based on the RF and XGBoost models suggests that aquifer hydraulic conductivity is the most critical controlling factor, followed by aquifer thickness and recharge, whereas land use and the remaining indicators exhibit comparatively lower contributions. The resulting vulnerability maps indicate that areas with high groundwater vulnerability are mainly concentrated in the western and southeastern parts of the study area, where agricultural activities are relatively intensive.

Whether groundwater Cr(VI) enrichment near landfills results from direct leachate input or geogenic mobilization remains unresolved. Groundwater and leachate hydrochemistry, a Cl⁻-based mixing model, PHREEQC inverse modeling, sediment Cr fractionation, and correlation analysis were used to investigate a loess-gully landfill in Northwest China. The site was divided into four groundwater environmental units along the flow path. Cr(VI) ranged from below detection to 0.170 mg/L, and 35% of samples exceeded the Class III limit (0.05 mg/L). At the near-source groundwater drainage outlet (II-GEU), Cr(VI) was below detection despite an 8.22% apparent leachate contribution. Downgradient, the contribution decreased to 5.12%, yet Cr(VI) reached 4.17 times the conservative-mixing estimate. Thus, direct leachate mixing cannot explain downstream enrichment. Near the landfill, organic-rich leachate favored reducing conditions and Cr(VI) reduction. Downgradient, increasingly oxidizing conditions limited Cr(VI) reduction, while SO₄²⁻ competed with chromate for mineral-surface adsorption sites, promoting Cr(VI) desorption and mobility. Leachate-induced mineral dissolution and cation exchange may further facilitate Cr(VI) migration by altering groundwater chemistry and mineral-surface properties. Landfill leachate therefore acts primarily as a geochemical trigger, inducing non-conservative transport and downstream release of geogenic Cr(VI), rather than as a direct Cr(VI) source. This mechanism has implications for monitoring and risk management in loess aquifers.