Machine Learning for Urban Heating Vector Estimation to Support City Decarbonization
Relevant features, transferability, and the role of spatial patterns
DOI:
https://doi.org/10.62161/sauc.v12.6400Keywords:
Artificial Intelligence, heating vector, decarbonization, machine learning, spatial analysis, climate zone, transferabilityAbstract
To support urban decarbonization, XGBoost classifiers were developed to predict residential heating energy vectors in Spain using open cadastral, census, and Energy Performance Certificate data. Training across climate zones C1, D1, and D3 evaluated the impact of non-spatial, coordinate-derived, and neighbour-corpus features. Spatially aware models achieved up to 73.6% accuracy, with neighbour energy probabilities providing the most significant gain and reducing misclassification clustering. However, transfer to cities without ground truth revealed instability (54.6% building-level agreement), underscoring the necessity of neighbourhood-level ground-truth collection to ensure reliable city-scale predictions.
Downloads
Global Statistics ℹ️
|
0
Views
|
0
Downloads
|
|
0
Total
|
|
References
Ali, U., Shamsi, M. H., Hoare, C., Mangina, E., & O’Donnell, J. (2019). A data-driven approach for multi-scale building archetypes development. Energy and Buildings, 202, 109364. https://doi.org/10.1016/j.enbuild.2019.109364
Anselin, L. (1995). Local Indicators of Spatial Association—LISA. Geographical Analysis, 27(2), 93-115. https://doi.org/10.1111/j.1538-4632.1995.tb00338.x
Badec, K. P., & Salam, P. A. (2024). Building Energy Performance Benchmarking: Current Methods, Applications, and Implications for the Philippines. 2024 International Conference on Sustainable Energy: Energy Transition and Net-Zero Climate Future (ICUE), 1-8. https://doi.org/10.1109/ICUE63019.2024.10795622
Beltrán-Velamazán, C., Monzón-Chavarrías, M., & López-Mesa, B. (2025). Predicting Energy and Emissions in Residential Building Stocks: National UBEM with Energy Performance Certificates and Artificial Intelligence. Applied Sciences, 15(2), 514. https://doi.org/10.3390/app15020514
BPIE (Buildings Performance Institute Europe). (2025). Delivering the EPBD: A guide towards better, affordable and more resilient buildings for all in Europe. https://www.bpie.eu/delivering-the-epbd-a-guide-towards-better-affordableand-more-resilient-buildings-for-all-in-europe/
Cerezo Davila, C. (2017). Building archetype calibration for effective urban building energy modeling [Massachusetts Institute of Technology]. http://hdl.handle.net/1721.1/111487
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research, 16, 321-357. https://doi.org/10.1613/jair.953
Chen, G., Lu, S., Zhou, S., Tian, Z., Kim, M. K., Liu, J., & Liu, X. (2025). A Systematic Review of Building Energy Consumption Prediction: From Perspectives of Load Classification, Data-Driven Frameworks, and Future Directions. Applied Sciences, 15(6), 3086. https://doi.org/10.3390/app15063086
Cities—United Nations Sustainable Development Action 2015. (s. f.). United Nations Sustainable Development. Recuperado 29 de julio de 2026, de https://www.un.org/sustainabledevelopment/cities/
Directive 2023/1791 of the European Parliament and of the Council on Energy Efficiency and Amending Regulation 2023/955, EP, CONSIL, 231 OJ L (2023). http://data.europa.eu/eli/dir/2023/1791/oj
Directive 2024/1275 of the European Parliament and of the Council on the Energy Performance of Buildings, EP, CONSIL (2024). http://data.europa.eu/eli/dir/2024/1275/oj
Economidou, M., Todeschi, V., Bertoldi, P., D’Agostino, D., Zangheri, P., & Castellazzi, L. (2020). Review of 50 years of EU energy efficiency policies for buildings. Energy and Buildings, 225, 110322. https://doi.org/10.1016/j.enbuild.2020.110322
Eguiarte, O., de Agustín-Camacho, P., & del Portillo-Valdés, L. (2022). Energy and economic analysis of domestic heating costs based on distributed energy resources: A case study in Spain. Energy Reports, Selected papers from 2022 7th International Conference on Advances on Clean Energy Research, 8, 56-61. https://doi.org/10.1016/j.egyr.2022.10.214
Eguiarte, O., Garrido-Marijuán, A., de Agustín-Camacho, P., del Portillo, L., & Romero-Amorrortu, A. (2020). Energy, Environmental and Economic Analysis of Air-to-Air Heat Pumps as an Alternative to Heating Electrification in Europe. Energies, 13(15), 3939. https://doi.org/10.3390/en13153939
EU Mission: Climate-Neutral and Smart Cities. (2026, julio 20). https://research-and-innovation.ec.europa.eu/funding/funding-opportunities/funding-programmes-and-open-calls/horizon-europe/eu-missions-horizon-europe/climate-neutral-and-smart-cities_en
Fang, C., Zhou, L., Gu, X., Liu, X., & Werner, M. (2025). A data driven approach to urban area delineation using multi source geospatial data. Scientific Reports, 15. https://doi.org/10.1038/s41598-025-93366-x
Harun, F., Pikas, E., Iliste, E., Hallik, J., & Kalamees, T. (2026). From static archetypes toward dynamic, condition-aware archetypes in UBEM: An integrative review with an illustrative case demonstration. Frontiers in Energy Research, 14. https://doi.org/10.3389/fenrg.2026.1800126
IDAE. (2026). SPAHOUSEC III. Estudio del consumo energético, equipamiento y hábitos de consumo de la energía del sector residencial en España. https://www.idae.es/sites/default/files/documentos/publicaciones_idae/20260123_SPAHOUSEC_III.pdf
Jiang, Q., Huang, C., Wu, Z., Yao, J., Wang, J., Liu, X., & Qiao, R. (2024). Predicting building energy consumption in urban neighborhoods using machine learning algorithms. Frontiers of Urban and Rural Planning, 2. https://doi.org/10.1007/s44243-024-00032-3
Li, K., Xue, W., Tan, G., & Denzer, A. S. (2020). A state of the art review on the prediction of building energy consumption using data-driven technique and evolutionary algorithms. Building Services Engineering Research & Technology, 41(1), 108-127. https://doi.org/10.1177/0143624419843647
Long, C., Yang, X., Su, Y., Liu, F., Ma, R., Ma, T., Wu, Y., & Shen, X. (2025). Air Conditioning Load Forecasting for Geographical Grids Using Deep Reinforcement Learning and Density-Based Spatial Clustering of Applications with Noise and Graph Attention Networks. Energies, 18(11), 2832. https://doi.org/10.3390/en18112832
Luqman, M., Rayner, P. J., & Gurney, K. R. (2023). On the impact of urbanisation on CO2 emissions. Npj Urban Sustainability, 3(1), 6. https://doi.org/10.1038/s42949-023-00084-2
Ministerio de Transportes, Movilidad y Agenda Urbana. Gobierno de España. (2019). Código Técnico de la Edificación: Documento Básico DB-HE Ahorro de Energía. https://www.codigotecnico.org/pdf/Documentos/HE/DBHE.pdf
Ministerio de Transportes, Movilidad y Agenda Urbana. Gobierno de España. (2025). Borrador del Plan Nacional de Renovación de Edificios (PNRE): Marco ARCE 2050. https://www.mivau.gob.es/recursos_mfom/audienciainfopublica/recursos/borrador_pnre.pdf
OECD. (2020). Strengthening Governance of EU Funds under Cohesion Policy: Administrative Capacity Building Roadmaps. OECD Multi‑level Governance Studies. https://doi.org/10.1787/9b71c8d8-en
Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345-1359. https://doi.org/10.1109/TKDE.2009.191
Reinhart, C. F., & Cerezo Davila, C. (2016). Urban building energy modeling – A review of a nascent field. Building and Environment, 97, 196-202. https://doi.org/10.1016/j.buildenv.2015.12.001
Rey, S. J., & Anselin, L. (2007). PySAL: A Python Library of Spatial Analytical Methods. Review of Regional Studies, 37(1). https://doi.org/10.52324/001c.8285
Roberts, D., Bahn, V., Ciuti, S., Boyce, M., Elith, J., Guillera-Arroita, G., Hauenstein, S., Lahoz-Monfort, J., Schröder, B., Thuiller, W., Warton, D., Wintle, B., Hartig, F., & Dormann, C. (2016). Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure. Ecography, 40. https://doi.org/10.1111/ecog.02881
Secretaría de estado de transportes, movilidad y agenda urbana. Gobierno de España. (2020). EREESE 2020. Actualización 2020 de la estrategia a largo plazo para la rehabilitación energética en el sector de la edificación en España. https://www.mivau.gob.es/recursos_mfom/paginabasica/recursos/eresee_2020.pdf
Shen, P., & Wang, H. (2024). Archetype building energy modeling approaches and applications: A review. Renewable and Sustainable Energy Reviews, 199, 114478. https://doi.org/10.1016/j.rser.2024.114478
Sisman, S., Kara, A., & Aydinoglu, A. C. (2025). Leveraging spatial data infrastructure for machine learning based building energy performance prediction. PLOS ONE, 20(10), e0335531. https://doi.org/10.1371/journal.pone.0335531
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Authors retain copyright and transfer to the journal the right of first publication and publishing rights
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.
Those authors who publish in this journal accept the following terms:
-
Authors retain copyright.
-
Authors transfer to the journal the right of first publication. The journal also owns the publishing rights.
-
All published contents are governed by an Attribution-NoDerivatives 4.0 International License.
Access the informative version and legal text of the license. By virtue of this, third parties are allowed to use what is published as long as they mention the authorship of the work and the first publication in this journal. If you transform the material, you may not distribute the modified work. -
Authors may make other independent and additional contractual arrangements for non-exclusive distribution of the version of the article published in this journal (e.g., inclusion in an institutional repository or publication in a book) as long as they clearly indicate that the work was first published in this journal.
- Authors are allowed and recommended to publish their work on the Internet (for example on institutional and personal websites), following the publication of, and referencing the journal, as this could lead to constructive exchanges and a more extensive and quick circulation of published works (see The Effect of Open Access).
