Evaluating pedestrian comfort in high-density cities requires methods integrating subjective experience with urban morphology. This study develops an integrated framework combining pairwise comparison scoring, semantic segmentation (DeepLabv3+), ensemble learning (Random Forest), and SHAP-based interpretability. EfficientNet-B7 is used to expand pairwise datasets and derive continuous comfort scores across Macau’s street network. Four experiential street types are identified: historical–cultural districts, urban lifestyle areas, natural corridors, and leisure zones. SHAP analysis illustrates stable associations between predicted comfort scores and multi-layered spatial configurations, including cultural legibility and sequencing in historic cores, moderate greenery with functional anchoring in residential areas, and scene coherence in tourism zones. Semantic features serve as effective morphological proxies within the modeling framework. Methodologically, the framework demonstrates how explainable machine learning can be applied to dense Asian cities under observational conditions. Design implications emphasize interface continuity, microclimate adaptation, and functional enrichment, suggesting that pedestrian comfort is closely related to coherent spatial–experiential structures rather than isolated environmental upgrades.
Gong et al. (Tue,) studied this question.