Daytime–Nighttime Contrasts in Morphology–LST Associations Across Urban Functional Zones Under Heatwave Conditions: Evidence from Beijing and Nanjing, China

Extreme heatwaves intensify urban heat islands and pose increasing risks to urban sustainability and human health. However, how urban morphology is associated with daytime and nighttime land surface temperature (LST) across urban functional zones (UFZs), particularly under heatwave conditions, remains insufficiently understood. To address this gap, this study integrates daytime and nighttime LST data derived from SDGSAT-1, multi-dimensional urban morphology indicators, and two interpretable ensemble models (XGBoost and GWRF) to investigate overall sample-level nonlinear model-based associations between urban morphology and LST and to explore spatial variation in local predictor importance within Beijing and Nanjing, China. Because the daytime and nighttime scenes were not always paired within the same heatwave episode, the analysis focuses on selected heatwave-condition observations. The results show marked contrasts between the selected daytime and nighttime observations in UFZ-level thermal patterns. Industrial zones generally exhibited the highest daytime LST, whereas residential zones showed the highest nighttime LST. Building density was identified as the primary model-based predictor of daytime LST in both cities, although its association with LST was nonlinear and varied across density ranges. In contrast, nighttime LST was characterized by more heterogeneous predictor associations, involving vegetation structure, sky openness, building form, anthropogenic indicators, and material-related variables, with their relative importance differing across cities and UFZ types. Local predictor-importance patterns also varied across neighborhoods, cities, and observation times, indicating that model-identified locally important predictors were not spatially uniform within each city. These findings highlight the potential of SDGSAT-1 daytime and nighttime thermal observations and interpretable machine learning for screening candidate local thermal priority areas and key morphology-related factors under heatwave conditions.