-
A Probabilistic Framework for Predicting Spatiotemporal Intensity and Variability of Outdoor Thermal Comfort
Authors:
Shisheng Chen,
Ruohan Xu,
Nyuk Hien Wong,
Shanshan Tong,
Jiashuo Wang,
Matthaios Santamouris
Abstract:
Thermal conditions in the urban canopy exhibit stochastic variability driven by varied radiative fluxes and turbulent wind fields, requiring probabilistic rather than deterministic prediction methods. This study presents a probabilistic framework for predicting the spatial and temporal intensity and variability of outdoor thermal comfort in tropical urban environments. The framework integrates gro…
▽ More
Thermal conditions in the urban canopy exhibit stochastic variability driven by varied radiative fluxes and turbulent wind fields, requiring probabilistic rather than deterministic prediction methods. This study presents a probabilistic framework for predicting the spatial and temporal intensity and variability of outdoor thermal comfort in tropical urban environments. The framework integrates ground-measured meteorological data and remote sensing urban morphological data to calculate Physiological Equivalent Temperature (PET), and applies K-means, XGBoost, and Monte Carlo simulations on PET training and inference. The prediction model achieved strong performance, with R2, RMSE, and SMAPE values of 0.93, 0.81 degC, and 1.34% for PET_mean, and 0.85, 0.38 degC, and 10.44% for PET_std, respectively. A case study showed clear spatial heterogeneity of outdoor thermal comfort. Locations with dense tree canopies and vegetated surfaces displayed a normalized percentage of acceptable thermal comfort (NATC) up to 65%, whereas built-up zones dominated by impervious surfaces, such as industrial estates and high-density residential areas, recorded NATC below 30%. Greenery was found to mitigate both the intensity of heat stress and its variability, producing a stable and comfortable microclimate. Daytime PET_std ranged from 4.0-4.5 degC in built-up areas to 1.5-2.0 degC in greenery-covered zones, while nighttime PET_std decreased to 2.2-2.4 degC and 1.2-1.4 degC, respectively. These findings emphasize the critical role of greenery in mitigating thermal variability and enhancing outdoor thermal comfort, while revealing the stochastic nature of thermal comfort across different urban morphologies.
△ Less
Submitted 9 December, 2025; v1 submitted 11 September, 2025;
originally announced September 2025.
-
Quantifying Key Design Factors for Thermal Comfort in Underground Space Through Global Sensitivity Analysis and Machine Learning
Authors:
Shisheng Chen,
Nyuk Hien Wong,
Chao Cen,
Ruohan Xu,
Lei Xu,
Zhenjiang Shen,
Zhigang Wu,
Jiayan Fu,
Zhongqi Yu
Abstract:
This study identified the key design factors related to thermal comfort in naturally ventilated underground spaces under high temperature conditions (outdoor Tmax = 42.9 C) in Fuzhou, China. Fuzhou has a humid subtropical climate and is one of the three hottest cities in China in 2024. Daytime measurements indicated reduced air temperature (AT), mean radiant temperature (MRT), and wind speed (V),…
▽ More
This study identified the key design factors related to thermal comfort in naturally ventilated underground spaces under high temperature conditions (outdoor Tmax = 42.9 C) in Fuzhou, China. Fuzhou has a humid subtropical climate and is one of the three hottest cities in China in 2024. Daytime measurements indicated reduced air temperature (AT), mean radiant temperature (MRT), and wind speed (V), together with elevated relative humidity (RH) in the underground space. Physiological Equivalent Temperature (PET) in the underground was consistently lower during peak hours (08:00-16:00), with the maximum difference in PET between pedestrian and underground levels being 11-11.9 C. Higher pedestrian-level PET at L1 was attributed to reduced greenery and shading, and decrement factors indicated greater thermal dampening at L2 (0.197) than at L1 (0.308). Sensitivity analysis showed that MRT was the most influential factor (S1/ST = 0.59-0.72) for aboveground spaces, followed by AT (0.13-0.26). In contrast, underground PET was mainly affected by metabolic rate (MET) (0.63-0.65), followed by RH (0.14-0.20) and V (0.08-0.18). Partial dependence analysis revealed that a 1 met increase in MET raised PET by 1.6 C, whereas a 1 m/s increase in V reduced PET by 1.5-2.2 C in the underground space. Due to cooler and more stable thermal conditions, underground spaces have higher tolerance for intensive physical activities. By buffering fluctuations in AT and MRT, underground environments can significantly alleviate heat stress and provide passive cooling shelter during daytime heat waves. Overall, this study provides empirical evidence to support underground space design in hot-humid climates and offers insights for sustainable urban heat mitigation.
△ Less
Submitted 24 November, 2025; v1 submitted 21 July, 2025;
originally announced July 2025.
-
Physics-Informed Regression Modelling for Vertical Facade Surface Temperature: A Tropical Case Study on Solar-reflective Material
Authors:
Shisheng Chen,
Shanshan Tong,
Nyuk Hien Wong,
May Lwin Oo,
Joie Lim,
Erna Tan,
Ruohan Xu,
Marcel Ignatius,
Yang He
Abstract:
Urban heat islands (UHIs) pose a critical challenge in densely populated cities and tropical climates where large amounts of energy are used to meet the cooling demand. To address this, Building and Construction Authority (BCA) of Singapore provides incentives for passive cooling such as using of solar-reflective material in its Green Mark guidelines. Thus, understanding about its real-world effec…
▽ More
Urban heat islands (UHIs) pose a critical challenge in densely populated cities and tropical climates where large amounts of energy are used to meet the cooling demand. To address this, Building and Construction Authority (BCA) of Singapore provides incentives for passive cooling such as using of solar-reflective material in its Green Mark guidelines. Thus, understanding about its real-world effectiveness in tropical urban environments is required. This study evaluated the effectiveness of solar-reflective cool paint using a hybrid modelling framework combining a transient physical model and data driven model through field measurements. Several machine learning algorithms were compared including multiple-linear regression (MLR), random forest regressor (RF), AdaBoost regressor (AB), extreme gradient boosting regressor (XGB), and TabPFN regressor (TPR). The results indicated that the transient physical model overestimated facade temperatures in the lower temperature ranges. The physics-informed MLR achieved best performance with improved accuracy for pre-cool paint (R2=0.96, RMSE=0.83C) and post-cool paint (R2=0.95, RMSE=0.65C) scenarios, reducing RMSE by 26% and 44%, respectively. The hybrid model also effectively predicted hourly heat fluxes revealing substantial reductions in surface temperature and heat storage with increasing albedo. The maximum net heat flux q_net was reduced by about 30-65 W/m2 in the post-cool paint stage (albedo = 0.73) compared to the pre-cool paint stage (albedo = 0.31). As albedo increases from 0.1 to 0.9, the sensitivity analysis predicts that the maximum daytime surface temperature will decrease by about 11C and the peak heat release of the net heat flux will decrease significantly from about 161 W/m2 to 27 W/m2.
△ Less
Submitted 6 February, 2026; v1 submitted 21 July, 2025;
originally announced July 2025.
-
Empirical model of campus air temperature and urban morphology parameters based on field measurement and machine learning in Singapore
Authors:
Zhongqi Yu,
Shisheng Chen,
Nyuk Hien Wong,
Marcel Ignatius,
Jiyu Deng,
Yueer He,
Daniel Jun Chung Hii
Abstract:
The rising air temperature caused by Urban Heat Island (UHI) effect has become a problem for Singapore, it not only affects the thermal comfort of outdoor microclimate environment, but also increases the cooling energy consumption of buildings. As part of a multiscale and multi-physics urban microclimate model, weather stations were installed at 15 points within kent ridge campus of National Unive…
▽ More
The rising air temperature caused by Urban Heat Island (UHI) effect has become a problem for Singapore, it not only affects the thermal comfort of outdoor microclimate environment, but also increases the cooling energy consumption of buildings. As part of a multiscale and multi-physics urban microclimate model, weather stations were installed at 15 points within kent ridge campus of National University of Singapore (NUS) and continuously recorded the microclimate data from February 2019 to May 2019. A Geographical Information System (GIS) map and 3D model were constructed for extracting urban morphology parameters such as BDG, PAVE, WALL and HBDG. Through a site survey, SVF and GnPR were calculated. By using multi-criteria linear regression and machine learning, this research investigated five regression models for prediction of outdoor air temperature including linear regression (LR), k-nearest neighbours (KNN), support vector regression (SVR), decision tree (DT) and random forests (RF). The analysis of variables by best subsets regression showed greenery played crucial role in the mitigation of both daytime and night-time UHI. Pedestrian level wind flow was helpful in heat release in the daytime. High-rise buildings provided self-shadowing to reduce ambient air temperature but higher SVF was harmful to heat release in the night-time. For regression models, RF had the best predictive performance. Average RMSE of RF was reduced by 4% to 29% compared to linear regression. The learning curve indicated that the predictive power of LR could not be improved by additional data provision. In contrast, the downward trend in bias and variance suggested that RF can benefit from the training of big data. During the deployment of learning algorithms, RF continued to outperform other learning algorithms.
△ Less
Submitted 20 November, 2019;
originally announced November 2019.