Application of human-centric digital twins: Predicting outdoor thermal comfort distribution in Singapore using multi-source data and machine learning Xin Liu a , Zhonghua Gou a,* , Chao Yuan b a School of Urban Design, Wuhan University, Wuhan, China b Department of Architecture, National University of Singapore, Singapore ARTICLE INFO Keywords: Outdoor thermal comfort Machine learning Multi-source data Activity intensity Urban environment ABSTRACT In the face of global climate warming, outdoor thermal comfort in urban settings is increasingly critical. However, accurately predicting residents’ thermal perceptions during outdoor activities remains challenging due to complex environmental dynamics. This study introduces a human- centered digital twin framework that integrates physiological data, atmospheric conditions, and urban building environment features, with multiple machine learning models employed to predict and analyze outdoor thermal comfort in different regions of Singapore. Among these methods, the Bayesian-tuned XGBoost model exhibits the highest accuracy (0.66), notably excelling in categorizing “Prefer cooler” and “Prefer no change” responses. SHAP value analysis identifies key influencing factors such as human activity intensity (heart rate), geographical location (longitude and latitude), meteorological conditions (solar azimuth angle, dew point temperature), and greenery (Normalized Difference Vegetation Index). Based on the most effec- tive machine learning method, this research develops a user-personalized real-time prediction model for urban thermal comfort perception. The extensive hourly grid-based prediction results illustrate the spatiotemporal variations in outdoor thermal comfort, highlighting preference dif- ferences across locations, seasons, and activity levels. Results underscore the efficacy of the human-centric digital twin approach and machine learning in managing urban thermal envi- ronments, leveraging multi-source data to complement traditional survey methods effectively. 1. Introduction In recent years, the exacerbation of global climate warming and urban heat island effects has led to a rise in the frequency of extreme high-temperature weather events, increasing the heat risk levels in urban outdoor environments (IPCC, 2023). Urban outdoor spaces, as primary areas for residents’ daily activities, directly affect their health and well-being through thermal comfort. However, existing research on urban thermal environments primarily focuses on the macro scale, relying on remote sensing technology, meteorological data, and energy balance models to analyze large-scale land surface temperatures and heat island effects. While these studies have provided valuable insights into the overall thermal characteristics of cities, they often overlook residents’ actual thermal comfort perceptions in complex urban settings. Meanwhile, studies at meso- and micro-scales focus more on assessing individuals’ * Corresponding author. E-mail address: zh.gou@whu.edu.cn (Z. Gou). Contents lists available at ScienceDirect Urban Climate journal homepage: www.elsevier.com/locate/uclim https://doi.org/10.1016/j.uclim.2024.102210 Received 5 August 2024; Received in revised form 22 October 2024; Accepted 10 November 2024 Urban Climate 58 (2024) 102210 Available online 16 November 2024 2212-0955/© 2024 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.