With urbanization advancing, urban land surface temperatures (LST) are rising, and air pollution is intensifying. LST is shaped by multiple atmospheric and surface processes, yet the combined association of PM_2.5 and CO₂ emissions with LST remains insufficiently understood at the urban agglomeration scale. This study focuses on the Beijing–Tianjin–Hebei urban agglomeration (BTHUA) in northern China and the Chengdu–Chongqing urban agglomeration (CCUA) in southern China. It quantitatively examines the spatial correspondence of PM_2.5 and anthropogenic CO₂ emissions, and their seasonal associations with LST. The XGBoost-SHAP model is used to characterize model-based attribution across six management-relevant groups (urban ventilation, blue infrastructure, green infrastructure, surface permeability, low-carbon transition, and air quality management). The results show that (1) cold seasons exhibit a stronger PM_2.5 and CO₂ emissions compound pressure index (CPI)-LST association, with significant positive CPI-LST relationships; (2) across different categories, areas with high pollution and high anthropogenic CO₂ emissions typically have higher LST. In summer, high–high categories reached mean LST of 33.5 °C in BTHUA and 31.1 °C in CCUA, whereas the low–low category showed the lowest winter mean LST values of −3.5 °C and 6.9 °C, respectively; and (3) in BTHUA, blue infrastructure accounted for the largest baseline-model share in category-level model attribution. Within CCUA, air quality management accounted for the largest baseline-model share in category-level model attribution, except during summer. These results provide model-based evidence for seasonally differentiated heat mitigation strategies from an urban agglomeration perspective.

Rising urban temperatures have become a critical constraint to urban ecosystem resilience and livability due to rapid urbanization. This study proposes a novel intra-city zoning scheme, named component morphological blocks (CMBs), which classifies built-up areas into six types characterized by multidimensional urban canopy morphologies. The XGBoost-SHAP model, optimized via Bayesian tuning, was employed to examine the relative contributions of 16 potential driving variables to block-scale land surface temperature (LST). The results show that: (1) LST gradually increases with increasing building density in the warm seasons. The average building height (BH) exhibits a positive correlation with shaded area, thereby reducing LST on the block scale; (2) hotspots are mainly concentrated in function-oriented blocks with hotspot distribution indices of 1.85, 1.96, 1.24, and 1.14, respectively. Coldspots are largely observed in blue–green space in the warm seasons; (3) BH dominates the LST across seasons, while the building-related factors make a prominent impact on LST in warm seasons. The contribution of vegetation canopy density is followed by BH during autumn and winter (12.2%, 10.9%); (4) a distinct transition occurs between summer normalized difference built-up index (NDBI) and fractional vegetation cover around an NDBI of 0.1. In winter, the interaction between 2D and 3D vegetation factors indicates a shift in their relative contributions from negative to positive as they increase. This study demonstrates that CMBs serve as an effective choice for characterizing LST patterns at the block scale, providing insights for sustainable urban development aimed at mitigating the urban heat island effect.