Scalable machine learning for urban thermal morphology classification: clustering high-resolution microclimate and dynamic mapping of radiant temperature

Abstract

Recent advances in ultra-fine and ultra-fast urban climate modelling have improved the identification and representation of complex urban environments. However, their practical application of Mean Radiant Temperature (MRT) time series generated by these tools remain difficult to interpret for non-expert stakeholders, necessitating a transduction of complex numerical data into actionable spatial information. Leveraging LUCIDiT—an ultra-fast simulation tool enabling high-resolution MRT maps across continuous urban domain—this research proposes a scalable, automated framework for classifying different “thermal morphologies” based on the MRT time series analysis. The capacity of unsupervised machine learning to capture the nonlinear relationships of urban morphology is investigated trough a rigorous comparison between a physics-based heuristic approach, a shape-based algorithm (K-Shape), and K-Means clustering applied to both engineered thermal features and MRT time series. Results demonstrate that applying K-Means directly to the raw time series outperforms the other methods in terms of both computational efficiency and mathematical robustness, as confirmed by the Silhouette Score and Davies-Bouldin Index. Furthermore, the physical accuracy and interpretability of the data-driven clusters are successfully validated by projecting the spatial outputs into a novel 2D Thermal Phase Space. This computationally efficient methodology, applicable at different urban scales, converts the physical complex and synergistic dynamics of the urban microclimate into intuitive and easy-to-use spatial thermal maps. It connects advanced numerical simulations to practical urban design, providing a compact representation of urban thermal behaviour and enables the large-scale identification of recurrent microclimatic patterns fundamental for urban heat mitigation strategies.

Keywords

Urban thermal classification / Machine Learning / High-resolution microclimate clustering / Urban sustainability / Resilience urban planning / Urban Mean Radiant Temperature

References

[1] Ali AAB, Mitra C, Rishal FH, Hossain RB. Mapping and predicting urban heat island intensity hotspots through a space–time machine learning framework in Bangladesh. Computational Urban Science, 2026, 6(1): 14

[2] AlKhaled SR, Middel A, Shaeri P, Buo I, Schneider FA. WebMRT: An online tool to predict summertime mean radiant temperature using machine learning. Sustainable Cities and Society, 2024, 115: 105861

[3] Alrababaa A, Shouman O, Ibrahim H, Khattab T, Shaheen E, Ibrahim HS. Machine learning enhanced urban analysis for forecasting morphogenesis and housing allocation in rapidly developing cities. Computational Urban Science, 2025, 5(1): 66

[4] Amengual A, Homar V, Romero R, Brooks HE, Ramis C, Gordaliza M, Alonso S. Projections of heat waves with high impact on human health in Europe. Global and Planetary Change, 2014, 119: 71-84

[5] Ansys | Engineering Simulation Software. (n.d.). Retrieved April 7, 2026, from https://www.ansys.com/

[6] Baia, M., Pierucci, G., & Balocco, C. (2026). LUCIDiT: A Lean Urban Comfort Intelligent Digital Twin for Quick Mean Radiant Temperature Assessment. Atmosphere, 17(3). https://doi.org/10.3390/atmos17030305

[7] Beck HE, Zimmermann NE, McVicar TR, Vergopolan N, Berg A, Wood EF. Present and future Köppen-Geiger climate classification maps at 1-km resolution. Scientific Data, 2018, 5(1): 180214

[8] Belhadi A, Djenouri Y, Nørvåg K, Ramampiaro H, Masseglia F, Lin JC-W. Space–time series clustering: Algorithms, taxonomy, and case study on urban smart cities. Engineering Applications of Artificial Intelligence, 2020, 95: 103857

[9] Brentan B, Meirelles G, Luvizotto E, Izquierdo J. Hybrid SOM+k-means clustering to improve planning, operation and management in water distribution systems. Environmental Modelling & Software, Special Issue on Environmental Data Science. Applications to Air Quality and Water Cycle, 2018, 106: 77-88

[10] Briegel F, Wehrle J, Schindler D, Christen A. 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

[11] Bröde P, Fiala D, Błażejczyk K, Holmér I, Jendritzky G, Kampmann B, Tinz B, Havenith G. Deriving the operational procedure for the Universal Thermal Climate Index (UTCI). International Journal of Biometeorology, 2012, 56(3): 481-494

[12] Brozovsky J, Radivojevic J, Simonsen A. Assessing the impact of urban microclimate on building energy demand by coupling CFD and building performance simulation. Journal of Building Engineering, 2022, 55: 104681

[13] Chen L, Yu B, Yang F, Mayer H. Intra-urban differences of mean radiant temperature in different urban settings in Shanghai and implications for heat stress under heat waves: A GIS-based approach. Energy and Buildings, 2016, 130: 829-842

[14] Choi HS. Choi HS. Urban complexity and spatial system in hyper-morphology. Human-centred design: Spatial cognition and hyper-morphology, 2025Springer Nature: 37-62

[15] Climatologia di Firenze 1991–2020. (n.d.). Consorzio LaMMA. Retrieved April 7, 2026, from http://www.lamma.toscana.it/clima-e-energia/climatologia/clima-firenze

[16] Crandall CG, González-Alonso J. Cardiovascular function in the heat-stressed human. Acta Physiologica, 2010, 199(4): 407-423

[17] Das S, Sun QC, Both A, Foster S. Greenery from apartments: Quantifying and comparing views with residents’ perceptions. Computational Urban Science, 2025, 5(1): 61

[18] Davies DL, Bouldin DW. A cluster separation measure. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1979, PAMI-1(2): 224-227

[19] De Jaeger I, Reynders G, Callebaut C, Saelens D. A building clustering approach for urban energy simulations. Energy and Buildings, 2020, 208: 109671

[20] Di Napoli C, Pappenberger F, Cloke HL. Assessing heat-related health risk in Europe via the Universal Thermal Climate Index (UTCI). International Journal of Biometeorology, 2018, 62(7): 1155-1165

[21] ENVI-met: Powerful Tools for Urban Cooling and Climate Adaptation. (n.d.). Retrieved April 7, 2026, from https://envi-met.com/microclimate-simulation-software/

[22] Fanger PO. Thermal comfort: Analysis and applications in environmental engineering, 1970Danish Technical Press

[23] Feng Y, Wang H, Wu J, Wang Y, Shi H, Zhao J. Exploring the impact of urban spatial morphology on land surface temperature: A case study in Linyi City, China. PLoS ONE, 2025, 20(1): e0317659

[24] Fontana, A. G., Nascimento, V. F., Ometto, J. P., & do Amaral, F. H. F. (2023). Analysis of past and future urban growth on a regional scale using remote sensing and machine learning. Frontiers in Remote Sensing, 4. https://doi.org/10.3389/frsen.2023.1123254

[25] Grimmond CSB, Oke TR. An evapotranspiration-interception model for urban areas. Water Resources Research, 1991, 27(7): 1739-1755

[26] Höppe P. The physiological equivalent temperature—A universal index for the biometeorological assessment of the thermal environment. International Journal of Biometeorology, 1999, 43(2): 71-75

[27] Hu J, Yang B, Guo C, Jensen CS. Risk-aware path selection with time-varying, uncertain travel costs: A time series approach. The VLDB Journal, 2018, 27(2): 179-200

[28] Iglesias F, Kastner W. Analysis of similarity measures in times series clustering for the discovery of building energy patterns. Energies, 2013, 6(2): 579-597

[29] Ikotun AM, Ezugwu AE, Abualigah L, Abuhaija B, Heming J. K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data. Information Sciences, 2023, 622: 178-210

[30] Intergovernmental Panel on Climate Change (IPCC). Climate change 2022 – Impacts, adaptation and vulnerability: Working group II contribution to the sixth assessment report of the Intergovernmental Panel on Climate Change, 2023Cambridge University Press

[31] Jiang L, Zhang Y, Jiang S, Ma X, Chen Y. Seasonal spatiotemporal variations in intra- and inter-local climate zones using complete urban surface temperature. Building and Environment, 2026, 289: 114114

[32] Johansson E, Thorsson S, Emmanuel R, Krüger E. Instruments and methods in outdoor thermal comfort studies—The need for standardization. Urban Climate, 2014, 10: 346-366

[33] Kastner P, Dogan T. Eddy3D: A toolkit for decoupled outdoor thermal comfort simulations in urban areas. Building and Environment, 2022, 212: 108639

[34] Ketterer C, Matzarakis A. Mapping the Physiologically Equivalent Temperature in urban areas using artificial neural network. Landscape and Urban Planning, 2016, 150: 1-9

[35] Kottek, M., Grieser, J., Beck, C., Rudolf, B., & Rubel, F. (2006). World Map of the Köppen-Geiger climate classification updated. Meteorologische Zeitschrift, 259–263. https://doi.org/10.1127/0941-2948/2006/0130

[36] Lau T-K, Chen Y-C, Lin T-P. Application of local climate zones combined with machine learning to predict the impact of urban structure patterns on thermal environment. Urban Climate, 2023, 52: 101731

[37] Laurinec, P., Lóderer, M., Vrablecová, P., Lucká, M., Rozinajová, V., & Ezzeddine, A. B. (2016). Adaptive Time Series Forecasting of Energy Consumption Using Optimized Cluster Analysis. 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW), 398–405. https://doi.org/10.1109/ICDMW.2016.0063

[38] Li, D., Hu, X., Rollo, J., Luther, M., Lu, M., & Liu, C. (2025). Spatial Cluster Characteristics of Land Surface Temperatures. Sustainability, 17(6). https://doi.org/10.3390/su17062653

[39] Lin, P., Gou, Z., Lau, S. S.-Y., & Qin, H. (2017). The Impact of Urban Design Descriptors on Outdoor Thermal Environment: A Literature Review. Energies, 10(12). https://doi.org/10.3390/en10122151

[40] Lindberg F, Holmer B, Thorsson S. SOLWEIG 1.0—Modelling spatial variations of 3D radiant fluxes and mean radiant temperature in complex urban settings. International Journal of Biometeorology, 2008, 52(7): 697-713

[41] Liu H, Li M, Yang C, Jia L. Application of time-series analysis to urban climate change assessment. International Journal of Environmental Science and Technology, 2025, 22(12): 11037-11044

[42] Liu, Y., Zhang, Y., Gong, S., Wang, Z., & Zhang, H. (2015). Analysis on the Performance of Ground Heat Exchangers in Ground Source Heat Pump Systems based on Heat Transfer Enhancements. Procedia Engineering, The 9th International Symposium on Heating, Ventilation and Air Conditioning (ISHVAC) Joint with the 3rd International Conference on Building Energy and Environment (COBEE), 12–15 July 2015, Tianjin, China, 121, 19–26. https://doi.org/10.1016/j.proeng.2015.08.1013

[43] MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. In Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Statistics: 5.1 (pp. 281–298). University of California Press. https://projecteuclid.org/ebooks/berkeley-symposium-on-mathematical-statistics-and-probability/Proceedings-of-the-Fifth-Berkeley-Symposium-on-Mathematical-Statistics-and/chapter/Some-methods-for-classification-and-analysis-of-multivariate-observations/bsmsp/1200512992

[44] Majidi, F. (2023). A Hybrid SOM and K-means Model for Time Series Energy Consumption Clustering (arXiv:2312.11475). arXiv. https://doi.org/10.48550/arXiv.2312.11475

[45] Manyanya, T., Nethengwe, N. S., Verbist, B., & Somers, B. (2024). Optimizing Local Climate Zones through Clustering for Surface Urban Heat Island Analysis in Building Height-Scarce Cities: A Cape Town Case Study. Climate, 12(9). https://doi.org/10.3390/cli12090142

[46] Marey A, Zou J, Goubran S, Wang LL, Gaur A. Urban morphology impacts on urban microclimate using artificial intelligence – A review. City and Environment Interactions, 2025, 28: 100221

[47] Mayer H, Höppe P. Thermal comfort of man in different urban environments. Theoretical and Applied Climatology, 1987, 38(1): 43-49

[48] Mistry R, Mehrotra S. Impact of urban climate landscape patterns on thermal environment in local climate zones of Bhopal City. Computational Urban Science, 2025, 5(1): 47

[49] Monteith, J. L. (1965) Evaporation and environment. Symposium Society Experimental Biolology, 19, 205–234.

[50] Morales-Esteban A, Martínez-Álvarez F, Scitovski S, Scitovski R. A fast partitioning algorithm using adaptive Mahalanobis clustering with application to seismic zoning. Computers & Geosciences, 2014, 73: 132-141

[51] Muthers S, Matzarakis A, Koch E. Summer climate and mortality in Vienna—A human-biometeorological approach of heat-related mortality during the heat waves in 2003. Wiener Klinische Wochenschrift, 2010, 122(17–18): 525-531

[52] Nevers C, Carmeliet J, Kubilay A, Derome D. Clustering-based characterization of urban microclimate zones using CFD derived time-series data. Urban Climate, 2025, 64: 102719

[53] Nicol F, Humphreys M. Derivation of the adaptive equations for thermal comfort in free-running buildings in European standard EN15251. Building and Environment, International Symposium on the Interaction between Human and Building Environment Special Issue Section, 2010, 45(1): 11-17

[54] Gianniou P., Liu X., Heller A., Nielsen P. S., Rode C. (2018). Clustering-based analysis for residential district heating data, Energy Conversion and Management, 165, 840–850. https://doi.org/10.1016/j.enconman.2018.03.015

[55] OpenStreetMap. (n.d.). OpenStreetMap. Retrieved May 28, 2026, from https://www.openstreetmap.org/

[56] Pantavou K, Fillon A, Li L, Maniadis Z, Nikolopoulos GK. Thermal indices for assessing the impact of outdoor thermal environments on human health: A systematic review of epidemiological studies. International Journal of Biometeorology, 2025, 69(8): 1843-1866

[57] Paparrizos J, Gravano L. K-shape: Efficient and accurate clustering of time series. SIGMOD Record, 2016, 45(1): 69-76

[58] Perini K, Chokhachian A, Dong S, Auer T. Modeling and simulating urban outdoor comfort: Coupling ENVI-Met and TRNSYS by grasshopper. Energy and Buildings, 2017, 152: 373-384

[59] Photovoltaic Geographical Information System (PVGIS)—Joint Research Centre. (2024). https://joint-research-centre.ec.europa.eu/photovoltaic-geographical-information-system-pvgis_en

[60] Pierucci, G., Baia, M., & Balocco, C. (2025). Urban Area Sustainability Analysis by Means of Integrated Microclimatic Measurement Techniques Combined with Thermal Comfort Modelling—A Pilot Project Application. Energies, 19(1). https://doi.org/10.3390/en19010217

[61] Putra MIJ, Phinn S. Integrating artificial neural network-cellular automata and bayesian weight of evidence for spatiotemporal analysis of urban change in Brisbane City. Computational Urban Science, 2026, 6(1): 13

[62] Rashtian Z, Tabatabaei Manesh M, Tahsildoost M, Zomorodian ZS. Data-driven real-time visualization of urban heat islands using mean radiant temperature for urban design. Energy and Buildings, 2025, 333: 115470

[63] Rousseeuw PJ. Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 1987, 20: 53-65

[64] Sanhudo L, Rodrigues J, Filho ÊV. Multivariate time series clustering and forecasting for building energy analysis: Application to weather data quality control. Journal of Building Engineering, 2021, 35: 101996

[65] Shi, T., Chen, M., Li, J., & Lu, G. (2025). Quantifying the driving force of urban morphologies on canopy urban heat island: A machine learning approach with educational application. Frontiers in Environmental Science, 13. https://doi.org/10.3389/fenvs.2025.1647596

[66] The COMSOL® Software Product Suite. (n.d.). COMSOL. Retrieved April 7, 2026, from https://www.comsol.com/products

[67] Torabi Moghadam S, Coccolo S, Mutani G, Lombardi P, Scartezzini J-L, Mauree D. A new clustering and visualization method to evaluate urban heat energy planning scenarios. Cities, 2019, 88: 19-36

[68] Xi R, Li M, Hou M, Fu M, Qu H, Liu D, Haruna CR. Deep dilation on multimodality time series for human activity recognition. IEEE Access, 2018, 6: 53381-53396

[69] Yerbury LW, Campello RJGB, Livingston GCJr, Goldsworthy M, O’Neil L. Comparing clustering approaches for smart meter time series: Investigating the influence of dataset properties on performance. Applied Energy, 2025, 391: 125811

[70] Zhao L, Oleson K, Bou-Zeid E, Krayenhoff ES, Bray A, Zhu Q, Zheng Z, Chen C, Oppenheimer M. Global multi-model projections of local urban climates. Nature Climate Change, 2021, 11(2): 152-157

Funding

EU Project, LIFE Energy + LIFE Climate - LIFE23-CCA-IT-LIFE ESCAPOS(EU Project)

RIGHTS & PERMISSIONS

The Author(s)