Land use change is closely related to land surface temperature (LST). Based on remote sensing data from 2001 to 2020, this study analyzed the spatiotemporal variations and driving mechanisms of daytime and nighttime LST in the Urumqi Metropolitan Area (UMA) by combining traditional methods with the eXtreme Gradient Boosting (XGBoost)-SHAP coupled model. Although the average LST trend in the region was one of warming, the pixel-level significance analysis indicated that statistically significant warming (p < 0.05) is concentrated mainly in the urban core (2.65% of the area), while the majority of the region (70%) showed a non-significant warming trend. LST displayed significant spatial clustering, with Moran's I remaining above 0.990, indicating a positive spatial autocorrelation in spatial distribution. With the advancement of urbanization, the proportion of impervious surfaces increased from 0.87% to 1.14%, while wastelands consistently accounted for approximately 50% of the total area. Different land use types showed distinct effects on the urban heat island (UHI) phenomenon: water bodies, grasslands, and forests played cooling roles, whereas barren land and impervious areas were the main heat contributors. The XGBoost-SHAP analysis further revealed that the importance ranking of driving factors has evolved over time. Among these factors, Elevation dominates, while the influence of population-related factors increased significantly in 2020. This study provides a scientific basis for regulating the thermal environment of cities in arid regions from the perspective of land use. This study provides a scientific basis for regulating the thermal environment of arid-region cities from the perspective of land use.