Rapid urbanization in the Yellow River Basin intensifies the conflict between urban expansion and the thermal environment, threatening ecological security and sustainable development. Utilizing multi-source data (2000–2023) including nighttime light (NTL) and land surface temperature (LST), this study applies spatial analysis and Geographically Weighted Regression (GWR) to explore the spatial associations between urban development and LST and its drivers across core cities. The results indicate significant spatiotemporal differentiation: mid-downstream cities exhibited contiguous urban expansion, whereas upstream growth remained constrained by local topography, with heat islands consistently concentrating in built-up areas. The warming rate decreased gradually from downstream (0.29–0.40 °C/year) to upstream (0.20–0.30 °C/year). The LST-NTL correlation strengthened notably in mid-downstream regions but remained moderate upstream. GWR analysis revealed that urban development intensity, represented by NTL, is the primary driver of LST increase downstream, while natural factors predominantly mitigate warming upstream. This long-term, multi-city comparison provides a scientific basis for precise urban heat island management and sustainable planning in the basin.

Ecological restoration in arid regions can enhance ecosystem functions but may coincide with groundwater stress. Using nine headwater basins of the Tarim River Basin, we analyzed a GRACE/GLDAS-derived groundwater storage anomaly (GWSA) proxy for 2003–2025 and four ecosystem services and the integrated index (ESI) for 2000–2025; joint analyses covered 2003–2025. Correlation analysis, joint-trend zoning, and CatBoost–SHAP characterized spatial mismatches and nonlinear associations. The GWSA proxy declined by −0.31 mm month⁻¹, with negative anomalies intensifying after 2020 and a northwest-decrease/southeast-increase pattern. Comparisons with groundwater-level anomalies showed moderate agreement at Aksu (r = 0.52) but weak, nonsignificant agreement at Cele (r = −0.08), indicating spatially heterogeneous reliability. Carbon storage, habitat quality, net primary productivity, and ESI increased, whereas sand retention declined. Areas with increasing ESI but decreasing GWSA accounted for 42.5% of the study area. Five CatBoost models achieved R² values of 0.868–0.977. Regarding ESI, SHAP identified a candidate transition near −18.6 mm, below which GWSA was associated with negative model contributions; human-footprint contributions became increasingly negative with disturbance. These statistical associations, rather than causal effects, demonstrate that ecosystem-service improvement does not necessarily indicate groundwater recovery.