Understanding the seasonal nonlinear relationship between urban heat island (UHI) and multidimensional urban morphological patterns is crucial for regulating the urban thermal environment. To address this, this study quantified the contributions and sensitivities of urban morphology to land surface temperature (LST) variations and revealed their influencing pathways across four seasons in Beijing, using automated machine learning, SHapley Additive exPlanations interpretation, partial dependence analysis, and structural equation modeling. The results showed significant seasonal variations at the grid scale of 200 m. It was revealed that Normalized Difference Vegetation Index (NDVI) emerged as the most significant indicator affecting LST, followed by building height (BH) and building coverage ratio (BCR), while sky view factor and frontal area index had the least impact. BH was more influential than NDVI, affecting LST during winter. Additionally, sensitivity analysis revealed that impervious surface area, BCR, and mean building volume had positive relationships with LST. In contrast, NDVI and BH negatively affected LST with a noticeable cooling effect, particularly in summer. Furthermore, the total effects of all indicators on LST were negative, with the greatest in spring and the least in winter. Three-dimensional indicators generally exhibited more pronounced direct and total effects than two-dimensional indicators, except in winter. These findings can offer valuable insights for regulating seasonal surface UHI to maximize thermal environmental benefits.
Wang et al. (Thu,) studied this question.