ArticleOpen Access http://dx.doi.org/10.26855/ea.2025.10.017
A Comprehensive Review of Intelligent Regulation Technologies for Urban Thermal Comfort: Integrating Digital Twins and Machine Learning
Tao Ma
College of Life and Environment Sciences, Huangshan University, Huangshan 242700, Anhui, China.
*Corresponding author: Tao Ma
Published: December 24,2025
Abstract
The accelerated pace of global urbanization and anthropogenic climate change means that the urban heat island (UHI) effect has become a critical challenge in urban management, having a big effect on how people are healthy, how energy is used, and how the Earth looks. The traditional way to deal with urban temperature environment, static simulation or simple physical model, is slow and does not provide a prediction accuracy sufficient to control complex urban systems. This review critically scrutinizes the transformative possibilities of integrating Digital Twin (DT) technology with Machine Learning (ML) algorithms so as to set up a sturdy, adaptive system for urban thermal comfort. Using digital twins to build an accurate copy of real urban space and then creating a continuously monitoring and simulating platform, and using machine learning to add intelligence to them and make them more intelligent, i.e., processing huge amounts of data to predict thermal behavior and automatically adjust the control strategy. This paper comprehensively analyzes the overall theoretical architecture of the DT-ML integration mechanism, introduces key technologies in the multi-source data collection process, explores representative surrogate modeling methods for quick simulation, and assesses various optimization methods for thermal regulation. Also, the current applications and always existent issues like computation overheads, data being heterogeneous, etc., are touched upon. The review ends with the idea that the mixing of DT and ML is where the future of precise city weather regulation is going - moving from being just a way to react when problems happen to a smart, aware system that can actually control things on its own.
Keywords
Urban Thermal Comfort; Digital Twins; Machine Learning; Urban Heat Island; Intelligent Control Systems
References
[1] Cho Y, Kim S, Lee J, et al. Low-cost urban heat environment sensing device with android platform for digital twin. HardwareX. 2024;20:e00598.
[2] Gao Y, Wang Z. Future urban heat island effect and heat risk in mountainous megacity: Multi-scenario simulations using machine learning model and the SD-PLUS model. Sustain Cities Soc. 2025;134:106915.
[3] Tehrani A A, Sobhaninia S, Nikookar N, et al. Data-driven approach to estimate urban heat island impacts on building energy consumption. Energy. 2025;316:134508.
[4] Elvira N, Eglantina H, Anamădălina B, et al. Big data-driven digital twin and spatial computing technologies, artificial intelligence robotic and multi-sensor fusion systems, and deep learning-based image processing and augmented reality algorithms in sustainable smart cities. Geopolit Hist Int Relat. 2024;16(1):98-112.
[5] Brook A, Ben-Dor E, Richter R. Modelling and monitoring urban built environment via multi-source integrated and fused remote sensing data. Int J Image Data Fusion. 2013;4(1):2-32.
[6] Xiaoqing H, Dongliang Z, Xiaosong Z. Energy management of intelligent building based on deep reinforced learning. Alex Eng J. 2021;60(1):1509-1517.
[7] Xi T, Wang M, Cao E, et al. Preliminary research on outdoor thermal comfort evaluation in severe cold regions by machine learning. Buildings. 2024;14(1):284.
[8] Derek H, Yangquan C. A digital twin framework for environmental sensing with sUAS. J Intell Robot Syst. 2022;105(1).
How to cite this paper
A Comprehensive Review of Intelligent Regulation Technologies for Urban Thermal Comfort: Integrating Digital Twins and Machine Learning
How to cite this paper: Tao Ma. (2025). A Comprehensive Review of Intelligent Regulation Technologies for Urban Thermal Comfort: Integrating Digital Twins and Machine Learning. Engineering Advances, 5(4), 230-234.
DOI: http://dx.doi.org/10.26855/ea.2025.10.017