Machine learning-based urban densification: extending roof ridge lines for sustainable housing extension using generative adversarial networks

Abstract

To address the challenges of global urbanization and housing shortages, implementing practical densification approaches often necessitates tailoring solutions based on the local context and prevailing housing typologies. However, such expansion strategies have been limited to unidirectional stacking or single-direction extensions while also heavily relying on designers' previous experience and subjective judgment. Therefore, this study proposes a novel machine learning (ML)-based framework for generating multi-directional house extension options, enabling efficient and contextually appropriate residential densification. Unlike existing approaches limited to unidirectional expansion and subjective designer input, our framework automatically identifies suitable land surfaces, conducts voxel-based generation of extensions, and incorporates customizable, structurally valid prefabricated components. A case study of Walthamstow, a neighborhood in North London, UK, demonstrates the framework's potential for significant residential densification. Key findings reveal that our proposed data-driven approach can generate scalable densification solutions tailored to diverse residential building types and neighborhoods, offering a promising strategy to reduce urban sprawl, alleviate the housing crisis, and minimize environmental impact through efficient, automated, and contextually sensitive design. This ML-based framework significantly advances automated densification strategies, providing a practical tool for sustainable urban development.

Keywords

Housing density / Densification / Machine learning / Generative adversarial networks (GAN) / Housing extension / Sustainable urban planning

References

[1] Abdrabo KI, Hamed H, Fouad KA, Shehata M, Kantoush SA, Sumi T, Elboshy B, Osman T. A methodological approach towards sustainable urban densification for urban sprawl control at the microscale: Case study of Tanta, Egypt. Sustainability, 2021.

[2] Albert, A., Strano, E., Kaur, J., & González, M. (2018). Modeling Urbanization Patterns with Generative Adversarial Networks. IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, 2095–2098. https://doi.org/10.1109/IGARSS.2018.8518032

[3] Allen J, Lu K. Modeling and prediction of future urban growth in the Charleston region of South Carolina: A GIS-based integrated approach. Conservation Ecology, 2003.

[4] Amer M, Attia S. Identification of sustainable criteria for decision-making on roof stacking construction method. Sustainable Cities and Society, 2019, 47: 101456.

[5] Amer M, Mustafa A, Teller J, Attia S, Reiter S. A methodology to determine the potential of urban densification through roof stacking. Sustainable Cities And Society, 2017, 35: 677-691.

[6] Attia, S. (2015, June 18). Overview and recommendation on urban densification potential in Liège, Belgium. International conference on high-quality retrofit and redensification with timber construction systems. https://orbi.uliege.be/handle/2268/182805

[7] Baduge SK, Thilakarathna S, Perera JS, Arashpour M, Sharafi P, Teodosio B, Shringi A, Mendis P. Artificial intelligence and smart vision for building and construction 4.0: Machine and deep learning methods and applications. Automation in Construction, 2022, 141: 104440.

[8] Benjdira B, Ammar A, Koubaa A, Ouni K. Data-efficient domain adaptation for semantic segmentation of aerial imagery using generative adversarial networks. Applied Sciences, 2020, 10(3): Article 3.

[9] Bibby, P., Henneberry, J., & Halleux, J.-M. (2018). Under the radar? ‘Soft’ residential densification in England, 2001–2011. Environment and Planning B: Urban Analytics and City Science. https://doi.org/10.1177/2399808318772842

[10] Bibri SE. Data-driven smart sustainable cities of the future: Urban computing and intelligence for strategic, short-term, and joined-up planning. Computational Urban Science, 2021, 1(1): 8.

[11] Bibri SE, Krogstie J, Kärrholm M. Compact city planning and development: Emerging practices and strategies for achieving the goals of sustainability. Developments in the Built Environment, 2020, 4: 100021.

[12] Bolton LT. Space ratio: A measure of density potentials in the built environment. Sustainable Cities and Society, 2021, 75: 103356.

[13] Brick Industry Association. (1992). Brick Masonry Material Properties.

[14] Broitman D, Koomen E. Residential density change: Densification and urban expansion. Computers, Environment and Urban Systems, 2015, 54: 32-46.

[15] Cacciaguerra, G., & Gatti, M. P. (2015). Urban Re-densification And Regeneration: 21st Century City Strategies. Retrieved December 10, 2024, from https://www.witpress.com/elibrary/wit-transactions-on-ecology-and-the-environment/193/33844

[16] Carta, S. (2022). Machine Learning and the City: Applications in Architecture and Urban Design. John Wiley & Sons.

[17] Casini, M. (2021). Construction 4.0: Advanced Technology, Tools and Materials for the Digital Transformation of the Construction Industry. Woodhead Publishing.

[18] Chew ZX, Wong JY, Tang YH, Yip CC, Maul T. Generative design in the built environment. Automation in Construction, 2024, 166: 105638.

[19] De Keersmaecker M-L, Frankhauser P, Thomas I. Using Fractal Dimensions for Characterizing Intra-urban Diversity: The Example of Brussels. Geographical Analysis, 2003, 35(4): 310-328.

[20] Dembski S, Hartmann T, Hengstermann A, Dunning R. Enhancing understanding of strategies of land policy for urban densification. Town Planning Review, 2020.

[21] Dempsey N, Brown C, Bramley G. The key to sustainable urban development in UK cities? The influence of density on social sustainability. Progress In Planning, 2012, 77(3): 89-141.

[22] Dempsey N, Jenks M. The future of the compact city. Built Environment, 2010, 36(1): 116-121.

[23] Deng Y, Gadocha S, Spitzer W, Prinz TGIS-based Identification of Densification Types, 2022REAL CORP

[24] Dubey, A., Naik, N., Parikh, D., Raskar, R., & Hidalgo, C. A. (2016). Deep Learning the City: Quantifying Urban Perception at a Global Scale. In B. Leibe, J. Matas, N. Sebe, & M. Welling (Eds.), Computer Vision – ECCV 2016 (pp. 196–212). Springer International Publishing. https://doi.org/10.1007/978-3-319-46448-0_12

[25] Eggimann S, Wagner M, Ho YN, Züger M, Schneider U, Orehounig K. Geospatial simulation of urban neighbourhood densification potentials. Sustainable Cities And Society, 2021, 72: 103068.

[26] Enserink B, Koppenjan J. Public participation in China: Sustainable urbanization and governance. Management of Environmental Quality, 2007, 18(4): 459-474.

[27] European Committee for Standardization (CEN). (2005). EN 1991–1–4: Eurocode 1: Actions on structures—Part 1–4: General actions—Wind actions. https://www.phd.eng.br/wp-content/uploads/2015/12/en.1991.1.4.2005.pdf

[28] Fang Z, Qi J, Fan L, Huang J, Jin Y, Yang T. A topography-aware approach to the automatic generation of urban road networks. International Journal of Geographical Information Science, 2022.

[29] Fu X, Sanchez TW, Li C, Junqueira JR. Deciphering public voices in the digital era. Journal Of The American Planning Association, 2024.

[30] Gan W, Zhao Z, Wang Y, Zou Y, Zhou S, Wu Z. Udgan: A new urban design inspiration approach driven by using generative adversarial networks. Journal of Computational Design and Engineering, 2024, 11(1): 305-324.

[31] Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative Adversarial Networks (No. arXiv:1406.2661). arXiv. https://doi.org/10.48550/arXiv.1406.2661

[32] Green, B. (2019). The Smart Enough City: Putting Technology in Its Place to Reclaim Our Urban Future. MIT Press.

[33] Haldar A, Mahadevan SReliability Assessment Using Stochastic Finite Element Analysis, 2000John Wiley & Sons

[34] He W, Chen M. Advancing urban life: A systematic review of emerging technologies and artificial intelligence in urban design and planning. Buildings, 2024, 14(3): Article 3.

[35] Hecht, R., Herold, H., Meinel, G., & Buchroithner, M. (2013). Automatic Derivation of Urban Structure Types from Topographic Maps by Means of Image Analysis and Machine Learning.

[36] Hughes RT, Zhu L, Bednarz T. Generative adversarial networks-enabled human–artificial intelligence collaborative applications for creative and design industries: A systematic review of current approaches and trends. Frontiers in Artificial Intelligence, 2021.

[37] Hussain, M., & Chen, D. (2018). Building-Level Change Detection from Large-Scale Historical Vector Data by Using Direct and a Three-Tier Post-classification Comparison. In O. Gervasi, B. Murgante, S. Misra, E. Stankova, C. M. Torre, A. M. A. C. Rocha, D. Taniar, B. O. Apduhan, E. Tarantino, & Y. Ryu (Eds.), Computational Science and Its Applications – ICCSA 2018 (pp. 300–316). Springer International Publishing. https://doi.org/10.1007/978-3-319-95168-3_20

[38] Hwang ISY. When does stacking become vertical sprawl?. The Sustainable City IV: Urban Regeneration and Sustainability, 2006, 1: 283-292.

[39] Illampas R, Charmpis DC, Ioannou I. Laboratory testing and finite element simulation of the structural response of an adobe masonry building under horizontal loading. Engineering Structures, 2014, 80: 362-376.

[40] Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2016). Image-to-Image Translation with Conditional Adversarial Networks (No. arXiv:1611.07004; Version 1). arXiv. https://doi.org/10.48550/arXiv.1611.07004

[41] Jamarani A, Haddadi S, Sarvizadeh R, Haghi Kashani M, Akbari M, Moradi S. Big data and predictive analytics: A systematic review of applications. Artificial Intelligence Review, 2024, 57(7): 176.

[42] Jiang F, Ma J, Webster CJ, Li X, Gan VJL. Building layout generation using site-embedded GAN model. Automation in Construction, 2023, 151: 104888.

[43] Kameni Nematchoua M, Sevin M, Reiter S. Towards sustainable neighborhoods in Europe: Mitigating 12 environmental impacts by successively applying 8 scenarios. Atmosphere, 2020, 11(6): Article 6.

[44] Khan AA, Amirkhani M, Martek I. Overcoming deterrents to modular construction in affordable housing: A systematic review. Sustainability, 2024, 16(17): Article 17.

[45] Kim JH. Linking land use planning and regulation to economic development: A literature review. Journal of Planning Literature, 2011, 26(1): 35-47.

[46] Kotulla T, Denstadli JM, Oust A, Beusker E. What does it take to make the compact city liveable for wider groups? Identifying key neighbourhood and dwelling features. Sustainability, 2019, 11(12): Article 12.

[47] Kumar P, Ofli F, Imran M, Castillo C. Detection of disaster-affected cultural heritage sites from social media images using deep learning techniques. Journal of Computing and Cultural Heritage, 2020, 13(3): 23:1–23:31.

[48] Lapworth A, McGregor J. Seasonal variation of the prevailing wind direction in Britain. Weather, 2008.

[49] Lehmann S. Sustainable urbanism: Towards a framework for quality and optimal density?. Future Cities and Environment, 2016, 2(1): 8.

[50] Li J, Li C. Characterizing urban spatial structure through built form typologies: A new framework using clustering ensembles. Land Use Policy, 2024, 141: 107166.

[51] Li, Y., Hu, Y., Tan, T., Yu, B., Li, J., & Fingrut, A. (2023). AR-Assisted Assembly in Self-Build Construction with Discrete Components: 30th EG-ICE International Workshop on Intelligent Computing in Engineering. https://www.ucl.ac.uk/bartlett/construction/research/virtual-research-centres/institute-digital-innovation-built-environment/30th-eg-ice-1

[52] Li Y, Yu B, Fingrut A, Li J. Design for manufacturing and assembly (DfMA) of standardized modular wood components. Technology|architecture + Design, 2023.

[53] Liang J, Miao H, Li K, Tan J, Wang X, Luo R, Jiang Y. A review of multi-agent reinforcement learning algorithms. Electronics, 2025, 14(4): Article 4.

[54] Marique A-F, Reiter S. Retrofitting the suburbs: Insulation, density, urban form and location. Environmental Management and Sustainable Development, 2014.

[55] Mindali O, Raveh A, Salomon I. Urban density and energy consumption: A new look at old statistics. Transportation Research Part A: Policy And Practice, 2004, 38(2): 143-162.

[56] Mohajeri N, Gudmundsson A, Scartezzini J-L. Statistical-thermodynamics modelling of the built environment in relation to urban ecology. Ecological Modelling, 2015, 307: 32-47.

[57] Mohajeri N, Walch A, Smith A, Gudmundsson A, Assouline D, Russell T, Hall J. A machine learning methodology to quantify the potential of urban densification in the Oxford-Cambridge Arc, United Kingdom. Sustainable Cities and Society, 2023, 92: 104451.

[58] Mondal B, Das DN, Dolui G. Modeling spatial variation of explanatory factors of urban expansion of Kolkata: A geographically weighted regression approach. Modeling Earth Systems and Environment, 2015, 1(4): 29.

[59] Naik N, Kominers SD, Raskar R, Glaeser EL, Hidalgo CA. Computer vision uncovers predictors of physical urban change. Proceedings of the National Academy of Sciences of the United States of America, 2017, 114(29): 7571-7576.

[60] Neuman M. The compact city fallacy. Journal of Planning Education and Research, 2005, 25(1): 11-26.

[61] Newton D. Generative deep learning in architectural design. Technology|architecture + Design, 2019, 3(2): 176-189.

[62] Oorschot L, Asselbergs T. New housing concepts: Modular, circular, biobased, reproducible, and affordable. Sustainability, 2021, 13(24): 24.

[63] Owusu, G. (2013). Coping with Urban Sprawl: A Critical Discussion of the Urban Containment Strategy in a Developing Country City, Accra.

[64] Panagopoulos T, González Duque JA, Bostenaru Dan M. Urban planning with respect to environmental quality and human well-being. Environmental Pollution, 2016, 208: 137-144.

[65] Pauleit, S., Fryd, O., Backhaus, A., & Jensen, M. b. (2020). Green Infrastructures to Face Climate Change in an Urbanizing World. In Encyclopedia of Sustainability Science and Technology (p. 1). Springer New York. https://doi.org/10.1007/978-1-4939-2493-6_212-3

[66] Pitarch Á, Ruá MJ, Reig L, Arín I. Contribution of roof refurbishment to urban sustainability. Sustainability, 2020, 12(19): Article 19.

[67] Reades J, De Souza J, Hubbard P. Understanding urban gentrification through machine learning. Urban Studies, 2019, 56(5): 922-942.

[68] Regona M, Yigitcanlar T, Hon C, Teo M. Artificial intelligence and sustainable development goals: Systematic literature review of the construction industry. Sustainable Cities and Society, 2024, 108: 105499.

[69] Schirmer, P. M., Zöllig, C., Müller, K., & Axhausen, K. W. (2015). Land use and transport microsimulation on the canton of Zürich using UrbanSim. Integrated Transport and Land Use Modeling for Sustainable Cities, 461–509.

[70] Simon, D. (2016). Rethinking sustainable cities: Accessible, green and fair. Policy Press.

[71] Son TH, Weedon Z, Yigitcanlar T, Sanchez T, Corchado JM, Mehmood R. Algorithmic urban planning for smart and sustainable development: Systematic review of the literature. Sustainable Cities And Society, 2023, 94: 104562.

[72] Song Q, Dou Z, Qiu W, Li W, Wang J, van Ameijde J, Luo D. The evaluation of urban spatial quality and utility trade-offs for post-COVID working preferences: A case study of Hong Kong. Architectural Intelligence, 2023, 2(1): 1.

[73] Song Q, Fang Y, Li M, van Ameijde J, Qiu W. Exploring the coherence and divergence between the objective and subjective measurement of streetscape perceptions at the neighborhood level: A case study in Shanghai. Environment and Planning B: Urban Analytics and City Science, 2024.

[74] Song Q, Huang Y, Li W, Chen F, Qiu W. Unraveling the effects of micro-level street environment on dockless bikeshare in Ithaca. Transportation Research Part D: Transport and Environment, 2024, 132: 104256.

[75] Sun M, Zhang F, Duarte F, Ratti C. Understanding architecture age and style through deep learning. Cities, 2022, 128: 103787.

[76] Sun P, Yan F, He Q, Liu H. The development of an experimental framework to explore the generative design preference of a machine learning-assisted residential site plan layout. Land, 2023, 12(9): Article 9.

[77] Tsai SL, Ochiai C, Deng CZ, Tseng MH. A sustainable post-disaster housing development framework for an indigenous Hao-cha community in Taiwan: Considering culture and livelihood in housing extensions. International Journal of Disaster Resilience in the Built Environment, 2021, 13(5): 583-600.

[78] UN-Habitat. (2013). State of the World’s Cities 2012/2013: Prosperity of Cities. Routledge. https://doi.org/10.4324/9780203756171

[79] van Ameijde, J. (2023). Data-Driven Urban Design: Conceptual and Methodological Constructs for People-Oriented Public Spaces. In P. Morel & H. Bier (Eds.), Disruptive Technologies: The Convergence of New Paradigms in Architecture (pp. 59–84). Springer International Publishing. https://doi.org/10.1007/978-3-031-14160-7_5

[80] van Doorn, L., Arnold, A., & Rapoport, E. (2019). In the Age of Cities: The Impact of Urbanisation on House Prices and Affordability. In R. Nijskens, M. Lohuis, P. Hilbers, & W. Heeringa (Eds.), Hot Property: The Housing Market in Major Cities (pp. 3–13). Springer International Publishing. https://doi.org/10.1007/978-3-030-11674-3_1

[81] Vuckovic, M., Mahdavi, A., Tauber, C., & Kiesel-, K. (2017). Generation and Evaluation of Alternative Urban Densification Scenarios. 15, 59–64. https://doi.org/10.26868/25222708.2017.018

[82] Wai CT, Yi PW, Olanrewaju OI, Abdelmageed S, Hussein M, Tariq S, Zayed T. A critical analysis of benefits and challenges of implementing modular integrated construction. International Journal of Construction Management, 2023.

[83] Wang L, Omrani H, Zhao Z, Francomano D, Li K, Pijanowski B. Analysis on urban densification dynamics and future modes in southeastern Wisconsin, USA. PLoS One, 2019, 14(3): e0211964.

[84] Wang W-C, Lim S-H. A study on the space expansion of temporary housing to utilize modular mock-up. Journal of the Architectural Institute of Korea Planning & Design, 2014, 30(4): 103-111.

[85] Wang Y-C, Shen J-K, Xiang W-N. Ecosystem service of green infrastructure for adaptation to urban growth: Function and configuration. Ecosystem Health and Sustainability, 2018.

[86] Watson V. Locating planning in the New Urban Agenda of the urban sustainable development goal. Planning Theory, 2016, 15(4): 435-448.

[87] Wei YD, Ewing R. Urban expansion, sprawl and inequality. Landscape and Urban Planning, 2018, 177: 259-265.

[88] Wu AN, Stouffs R, Biljecki F. Generative adversarial networks in the built environment: A comprehensive review of the application of GANs across data types and scales. Building and Environment, 2022, 223: 109477.

[89] Xu H, Omitaomu F, Sabri S, Zlatanova S, Li X, Song Y. Leveraging generative AI for urban digital twins: A scoping review on the autonomous generation of urban data, scenarios, designs, and 3D city models for smart city advancement. Urban Informatics, 2024, 3(1): 29.

[90] Yang R, Xu Q, Long H. Spatial distribution characteristics and optimized reconstruction analysis of China’s rural settlements during the process of rapid urbanization. Journal of Rural Studies, 2016, 47: 413-424.

[91] Yao L, Peng K, Li C, Huang Y. Decoding urban form through street networks: A nationwide analysis of Chinese cities. Cities, 2025, 158: 105711.

[92] Zeleznikow J. Using artificial intelligence to provide intelligent dispute resolution support. Group Decision and Negotiation, 2021, 30(4): 789-812.

[93] Zhao P. Sustainable urban expansion and transportation in a growing megacity: Consequences of urban sprawl for mobility on the urban fringe of Beijing. Habitat International, 2010, 34(2): 236-243.

[94] Zheng H, Yuan PF. A generative architectural and urban design method through artificial neural networks. Building And Environment, 2021, 205: 108178.

[95] Zhu Y, Wang Y, Li J, Song Q, Chen D, Qiu W. Bikesharegan: Predicting dockless bike-sharing demand based on satellite image. Journal Of Transport Geography, 2025, 126: 104245.

RIGHTS & PERMISSIONS

The Author(s)