Vegetation drought is a critical manifestation of ecosystem vulnerability in high-altitude, water-limited regions under climate change. The Yellow River Water Conservation Area (YRWC), as the core water source of the Yellow River Basin, is highly sensitive to variations in hydrothermal conditions. In this study, a Temperature–Vegetation–Precipitation Drought Index (TVPDI) was constructed to characterize the spatio-temporal dynamics of vegetation drought in the YRWC for 2003, 2012, and 2019. The XGBoost–SHAP framework was further employed to quantitatively analyze the nonlinear response characteristics and relative contributions of key factors within the TVPDI framework. Scenario-based spatial simulations of vegetation drought for 2035 are then conducted based on the GeoSOS-FLUS model. The results indicate that vegetation drought in the YRWC exhibits a relatively stable spatial pattern, with drought severity gradually intensifying from southeast to northwest and moderate drought as the dominant type. Precipitation is the key variable of TVPDI, followed by land surface temperature, while NDVI mainly plays a nonlinear regulatory role. Among external factors, atmospheric moisture conditions show relatively higher explanatory relevance, whereas topographic and human activity factors exert comparatively weaker influences. Scenario-based simulation results suggest that vegetation drought may be alleviated under low-emission pathways, whereas high-emission scenarios substantially exacerbate drought severity and associated risks. This study presents an interpretable, index-based analytical framework combined with scenario-based spatial simulation for characterizing vegetation drought in the YRWC, thereby providing scientific support for ecological management and climate adaptation strategies in the Yellow River Basin.

Studying the impact of extreme climate events on vegetation dynamics is crucial for maintaining ecosystem stability. Based on ERA5-Land temperature and precipitation data, as well as MOD13C2 data, this study employs Pearson correlation analysis, wavelet analysis, and the XGBoost-SHAP model to analyze the response of the Normalized Difference Vegetation Index (NDVI) in China to extreme climate variations. The findings reveal the following. (1) NDVI increased steadily at a rate of 0.021/10 yr from 2001 to 2024. Extreme temperature and precipitation indices show an increasing trend in most regions. (2) NDVI was positively correlated with most extreme temperature and precipitation indices, and showed a significant negative correlation exclusively with Frost Days FDO (Frost Days) and CDD (Consecutive Dry Days). (3) R25 (Number of Heavy Precipitation Days) and SDII (Simple daily intensity index) are the primary drivers of nationwide NDVI changes, with contribution rates of 31.6% and 12.5%. Extreme climate indices can significantly affect vegetation growth when surpassing certain thresholds. For instance, the thresholds for R25 and SDII are 1.85 days and 4.35 mm/day. This study provides a scientific basis for understanding and managing vegetation responses to increasing climate extremes.