Journal of Urban Environmental Management

Presenting a hybrid method based on deep learning to predict the Universal Thermal Climate Index in urban open spaces.

Authors

Azam Noroozi 1
Mohammad Mohammadi 2

1 Assistant Prof., Department of Civil and Architecture, Faculty of Engineering, University of Torbat Heydarih, Torbat Heydarih, Iran.

2 Department of Computer Engineering, Bozorgmehr University of Qaenat, Qaen, Iran

https://doi.org/10.48306/juem.2025.544353.1094
Abstract
The design of sustainable spaces has become of great importance due to the impact of thermal comfort in urban open spaces on the feeling of comfort and satisfaction of citizens, as well as the optimal use of environmental conditions in creating comfort and saving energy consumption. Accurate prediction of thermal comfort and environmental thermal conditions in urban areas by various methods facilitates the improvement of urban planning and energy management. A review of previous studies shows the high ability of deep learning models in improving thermal comfort predictions. In this paper, a hybrid method based on deep learning is presented for predicting the universal thermal climate index. After preprocessing the dataset, the previous models that had high accuracy were trained and evaluated. Then, the three models with the highest performance were selected for the combined model, and the predictions of all three models were generated for the test set. To ensure dimensionality integrity, the predictions were converted into one-dimensional arrays. Finally, the final prediction was calculated by averaging the predictions of the three models. To evaluate the performance of the proposed model and to train and test the methods used in the combined model, the real data set of Mashhad city was used. Standard numerical prediction criteria including root mean square error, mean absolute error and coefficient of determination were calculated to evaluate the proposed model. The evaluation results showed that the hybrid model provides better performance in predicting the universal thermal climate index compared to previous methods.

Keywords

Urban open space
thermal comfort
Universal Thermal Climate Index
(UTCI) prediction
1. Galal, O. M.; Sailor, D. J.; Mahmoud, H. The impact of urban form on outdoor thermal comfort in hot arid environments during daylight hours, case study: New Aswan. Building and Environment. 2020;184:107222. DOI: 10.1016/j.buildenv.2020.107222
2. Jia, S.; et al. A hybrid framework for assessing outdoor thermal comfort in large-scale urban environments. Landscape and Urban Planning. 2025;256:105281. DOI: 10.1016/j.landurbplan.2024.105281
3.Jing, W.; et al. Evaluating thermal comfort indices for outdoor spaces on a university campus. Scientific Reports. 2024;14(1):21253. DOI: 10.1038/s41598-024-71805-5
4. Hataminejad, H.; Arvin, M.; Mohammadivanani, A.; Bzrafkan, S. Analysis of the spatial crimes dispersion in urban parks (case study: Parks Tehran city). Strategic Research on Social Problems. 2017;6(2):89-104. DOI: 10.22108/ssoss.2017.22146
5.Ahmadi, M.; Dadashi, A. The Identification of Urban Thermal Islands based on an Environmental Approach, Case Study: Isfahan Province. Geography and Environmental Planning. 2017;28(3):1-20. DOI: 10.22108/gep.2017.98318.0
6.Megri, A. C.; El Naqa, I. Prediction of the thermal comfort indices using improved support vector machine classifiers and nonlinear kernel functions. Indoor and Built Environment. 2014;25(1):6-16. DOI: 10.1177/1420326X14539693
7.    Veisi, O.; Attarhay Tehrani, A.; Gharaei, B.; Shakibamanesh, A. Using Artificial Intelligence for Predicting Universal Thermal Climate Index Based on Different Urban Conditions: A Comparative Study of Machine Learning Models. SSRN. DOI: 10.2139/ssrn.4840700
8.    Kuzmanović, D.; Banko, J.; Skok, G. Improving the operational forecasts of outdoor Universal Thermal Climate Index with post-processing. International Journal of Biometeorology. 2024;68(5):965–977. DOI: 10.1007/s00484-024-02640-6
9.    Shah, R.; Pandit, R.; Gaur, M. Urban physics and outdoor thermal comfort for sustainable street canyons using ANN models for composite climate. Alexandria Engineering Journal. 2022;61(12):10871–10896. DOI: 10.1016/j.aej.2022.04.024
10.  Briegel, F.; et al. High-resolution multi-scaling of outdoor human thermal comfort and its intra-urban variability based on machine learning. Geoscientific Model Development. 2024;17(4):1667–1688. DOI: 10.5194/gmd-17-1667-2024
11.  Yang, Z.; et al. GloUTCI-M: a global monthly 1 km Universal Thermal Climate Index dataset from 2000 to 2022. Earth System Science Data. 2024;16(5):2407–2424. DOI: 10.5194/essd-16-2407-2024
12.  Zhong, G. Convolutional Neural Network Model to Predict Outdoor Comfort UTCI Microclimate Map. Atmosphere. 2022;13(11):1860. DOI: 10.3390/atmos13111860
13.  Liu, T.; et al. Outdoor Thermal Comfort Research and Its Implications for Landscape Architecture: A Systematic Review. Sustainability. 2025;17(5):2330. DOI: 10.3390/su17052330
14.  Anders, J.; et al. Simplifying heat stress assessment: Evaluating meteorological variables as single indicators of outdoor thermal comfort in urban environments. Building and Environment. 2025;274:112658. DOI: 10.1016/j.buildenv.2025.112658
15.  Ahmadi, M. M.; Amini Zadeh, B.; Aqamalai, R. Thermal performance assessment of urban fabric in Tehran climate: lessons for climate-responsive urban design. Journal of Fine Arts: Architecture and Urbanism. 2020;25(1):5–15. DOI: 10.22059/jfaup.2020.296175.672397
16.  Lee, H.; Park, S.; Mayer, H. Approach for the vertical wind speed profile implemented in the UTCI basics blocks UTCI applications at the urban pedestrian level. International Journal of Biometeorology. 2025;69(3):567–580. DOI: 10.1007/s00484-025-02915-6
17.  Entezari, A.; Mayvaneh, F.; Rezaie, K.; Rahimi, F. An adaptive estimation method to predict thermal comfort indices using deep belief neural networks. Journal of Geographic Sciences (JGS). 2018;18(51):23–40. DOI: 10.29252/jgs.18.51.23
18.  Solcast. Available from: https://solcast.com/.
19.  Palma, W. Time Series Analysis. John Wiley & Sons; 2016.
20.  Han, J.; Kamber, M.; Pei, J. Data Mining: Concepts and Techniques. Waltham: Morgan Kaufmann Publishers; 2012.

  • Receive Date 31 August 2025
  • Revise Date 26 September 2025
  • Accept Date 28 October 2025
  • First Publish Date 28 October 2025
  • Publish Date 23 September 2025

Home

Guide for Authors

Submit Manuscript

Reviewers

Contact Us