A measurement-based framework integrating machine learning and morphological dynamics for outdoor thermal regulation.

This study presents a comprehensive investigation into the interplay between machine learning (ML) models, morphological features, and outdoor thermal comfort (OTC) across three key indices: Universal Thermal Climate Index (UTCI), Physiological Equivalent Temperature (PET), and Predicted Mean Vote (PMV). Based on a comprehensive field measurement for 173 urban canyons, proper dataset for summer outdoor thermal condition was provided. Concurrently, six distinct ML models were evaluated and optimized using Bayesian optimization (BO) technique, considering performance indicators like weighted accuracy, F1-Score, precision, and recall. Notable trends emerged, with the CatBoost Classifier demonstrating superior performance in UTCI prediction, the Random Forest classifier excelling in PET estimation, and the XGBoost Classifier achieving optimal PMV prediction. Furthermore, the study delved into the influence of morphological features on OTC, prioritizing factors using SHAP values. Results consistently identified 90-degree orientation, street width, and 180-degree orientation as pivotal factors influencing OTC, with varying degrees of sensitivity across different classifications of thermal stress. Analysis of binary SHAP values unveiled intricate relationships between urban features and OTC indices, emphasizing the critical influence of street orientation on regulating outdoor thermal environments for UTCI and PET scenarios. Surprisingly, street width emerged as the foremost influential factor within the PMV index, challenging established trends and highlighting the complexity of thermal comfort modeling. Additionally, current research delineates the multifaceted impact of street width on microclimate dynamics, enriching our understanding of urban thermal dynamics and emphasizing its role in mitigating thermal stress within urban environments.