Soil environmental quality in arid oases is crucial for regional ecological security but faces multi-source heavy metal (HM) contamination risks. This study aimed to (1) characterize the spatial distribution of soil HMs (As, Cd, Cr, Cu, Hg, and Zn) in the Ka Shi gar oasis, Xinjiang, (2) quantify the driving effect of irrigation water, and (3) elucidate interactions between HMs, soil properties, and land use types. Using 591 soil and 12 irrigation water samples, spatial patterns were mapped via inverse distance weighting interpolation, with drivers and interactions analyzed through correlation and land use comparisons. Results revealed significant spatial heterogeneity in HMs with no consistent regional trend: As peaked in arable land (5.27–40.20 μg/g) influenced by parent material and agriculture, Cd posed high ecological risk in gardens (max 0.29 μg/g), and Zn reached exceptional levels (412.00 μg/g) in gardens linked to industry/fertilizers. Irrigation water impacts were HM-specific: water contributed to soil As enrichment, whereas high water Cr did not elevate soil Cr (indicating industrial dominance), and Cd/Cu showed no significant link. Interactions with soil properties were regulated by land use: in arable land, As correlated positively with EC/TN and negatively with pH; in gardens, HMs generally decreased with pH, enhancing mobility risk; in forests, SOM adsorption immobilized HMs; in construction land, Hg correlated with SOM/TP, suggesting industrial-organic synergy. This study advances understanding by demonstrating that HM enrichment arises from natural and anthropogenic factors, with the spatial heterogeneity of irrigation water’s driving effect critically regulated by land use type, providing a spatially explicit basis for targeted pollution control and sustainable oasis management.

Drought is one of the major disasters constraining crop production. The accurate identification of the dominant environmental factors that drive drought stress at different growth stages of maize is essential for developing stage-specific and precise water management strategies, enhancing drought resistance, and ensuring food security. However, a key challenge is quantifying the nonlinear interactions among multiple environmental factors. This study focuses on the rain-fed agricultural region of Northwest China. To address the limited availability of drought event samples in this region and the inadequacy of traditional statistical methods in capturing complex inter-factor relationships, we integrate a small-sample modeling framework based on an improved Conditional Generative Adversarial Network (CGAN) with an attribution framework that employs SHapley Additive exPlanations (SHAP) for interpretability analysis. We incorporate ten environmental factors derived from multi-source remote sensing: temperature (T_max, T_min, T_mean), precipitation (P), evapotranspiration (ET), soil moisture at 0–10 cm (SM_0–10) and at 10–40 cm (SM_10–40), and solar-induced chlorophyll fluorescence (SIF_max, SIF_min, SIF_mean). Sample sets were established for different maize phenological stages. The CGAN model was employed to achieve high-precision estimation of maize drought severity levels, while the SHAP method was used to quantitatively analyze the dominant factors and their contributions at each phenological stage. The results show that the CGAN model achieved coefficients of determination (R²) of 0.963, 0.972, and 0.979 for the seedling, jointing–tasseling, and maturity stages, respectively, demonstrating excellent nonlinear modeling capability under small samples. SHAP analysis reveals a clear dynamic evolution of dominant factors across phenological stages. Evapotranspiration (ET) dominated in the seedling stage, reflecting the primary role of surface water–heat balance, while the jointing–tasseling stage transitioned to a co-dominance of ET, topsoil moisture (SM_0–10), and minimum SIF, indicating intensified crop transpiration and physiological stress under the meteorological drought framework, and the maturity stage shifted to an absolute dominance centered on mean temperature (T_mean), highlighting the critical impact of heat stress. This study provides a data-driven quantitative perspective for understanding maize drought mechanisms and offers a scientific basis for formulating differentiated drought management strategies for different growth stages. Furthermore, it demonstrates the potential of integrating CGAN with SHAP for agricultural remote sensing and drought attribution research in data-scarce regions.