Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Perspective
  • Published:

Large language models in urban planning

Nature Cities volume 2, pages 585–592 (2025)Cite this article

Subjects

Abstract

The advanced computational capabilities of artificial intelligence, particularly large language models such as OpenAI’s ChatGPT, offer great potential for addressing the complex developmental challenges faced by cities globally. These challenges are those that traditional urban planning methods often struggle to tackle. We explore how large language models can be leveraged to automate and support various urban planning tasks, providing nuanced computational support and advanced analytical capabilities. We highlight potential applications throughout the planning process and discuss the barriers and challenges involved. By setting a research agenda, we aim to foster the integration of artificial intelligence in urban planning, enhancing the field’s ability to create positive, inclusive and effective urban solutions.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Conceptual framework of the capabilities of LLMs in urban planning.

Similar content being viewed by others

References

  1. Batty, M. Artificial intelligence and smart cities. Environ. Plan. B Urban Anal. City Sci. 45, 3–6 (2018).

    Article  Google Scholar 

  2. Marasinghe, R., Yigitcanlar, T., Mayere, S., Washington, T. & Limb, M. Computer vision applications for urban planning: a systematic review of opportunities and constraints. Sustain. Cities Soc. 100, 105047 (2023).

    Article  Google Scholar 

  3. Berry, B. J. Cities as systems within systems of cities. Pap. Reg. Sci. 13, 147–163 (1964).

    Article  Google Scholar 

  4. Jacobs, J. The Death and Life of Great American Cities 1st edn (Random House, 1961)

  5. Alexander, C. A city is not a tree. Ekistics 139, 344–348 (1965).

    Google Scholar 

  6. Cejudo, G. M. & Michel, C. L. Addressing fragmented government action: coordination, coherence, and integration. Policy Sci. 50, 745–767 (2017).

    Article  Google Scholar 

  7. Schipper, E. L. F. Maladaptation: when adaptation to climate change goes very wrong. One Earth 3, 409–414 (2020).

    Article  Google Scholar 

  8. Wegener, M. Operational urban models: state-of-the-art. J. Am. Plann. Assoc. 60, 17–29 (1994).

    Article  Google Scholar 

  9. Klosterman, R. E. Large-scale urban models: retrospect and prospect. J. Am. Plann. Assoc. 60, 3–6 (1994).

    Article  Google Scholar 

  10. Harris, T. M. & Elmes, G. A. The application of GIS in urban and regional planning: a review of the North American experience. Appl. Geogr. 13, 9–27 (1993).

    Article  Google Scholar 

  11. Geertman, S. & Stillwell, J. Planning support systems: an inventory of current practice. Comput. Environ. Urban Syst. 28, 291–310 (2004).

    Article  Google Scholar 

  12. Pettit, C. et al. Planning support systems for smart cities. City Cult. Soc. 12, 13–24 (2018).

    Article  Google Scholar 

  13. Caldarelli, G. et al. The role of complexity for digital twins of cities. Nat. Comput. Sci. 3, 374–381 (2023).

    Article  Google Scholar 

  14. Andrews, C. et al. White Paper on AI in Planning (American Planning Association, 2022)

  15. Batty, M. & Yang, W. A Digital Future for Planning: Spatial Planning Reimagined (Digital Task Force for Planning, 2022)

  16. Sanchez, T. W., Shumway, H., Gordner, T. & Lim, T. The prospects of artificial intelligence in urban planning. Int. J. Urban Sci. 27, 179–194 (2023).

    Article  Google Scholar 

  17. Thackway, W., Ng, M., Lee, C.-L. & Pettit, C. Implementing a deep-learning model using Google street view to combine social and physical indicators of gentrification. Comput. Environ. Urban Syst. 102, 101970 (2023).

    Article  Google Scholar 

  18. Yin, L. & Wang, Z. Measuring visual enclosure for street walkability: using machine learning algorithms and Google Street View imagery. Appl. Geogr. 76, 147–153 (2016).

    Article  Google Scholar 

  19. Lock, O., Bain, M. & Pettit, C. Towards the collaborative development of machine learning techniques in planning support systems – a Sydney example. Environ. Plan. B Urban Anal. City Sci. 48, 484–502 (2021).

    Article  Google Scholar 

  20. Lee, H. & Li, W. Improving interpretability of deep active learning for flood inundation mapping through class ambiguity indices using multi-spectral satellite imagery. Remote Sens. Environ. 309, 114213 (2024).

    Article  Google Scholar 

  21. Fu, X. Natural language processing in urban planning: a research agenda. J. Plan. Lit. https://doi.org/10.1177/08854122241229571 (2024)

  22. Lee, D. B. Retrospective on large-scale urban models. J. Am. Plann. Assoc. 60, 35–40 (1994).

    Article  Google Scholar 

  23. Harris, B. & Batty, M. Locational models, geographic information and planning support systems. J. Plan. Educ. Res. 12, 184–198 (1993).

    Article  Google Scholar 

  24. Klosterman, R. E. Planning support systems: a new perspective on computer-aided planning. J. Plan. Educ. Res. 17, 45–54 (1997).

    Article  Google Scholar 

  25. Vonk, G., Geertman, S. & Schot, P. A SWOT analysis of planning support systems. Environ. Plan. A 39, 1699–1714 (2007).

    Article  Google Scholar 

  26. Feenberg, A. Critical Theory of Technology Vol. 5 (Oxford Univ. Press, 1991)

  27. Fu, X., Wang, R. & Li, C. Can ChatGPT evaluate plans? J. Am. Plann. Assoc. 90, 525–536 (2024).

    Article  Google Scholar 

  28. Fu, X., Sanchez, T. W., Li, C. & Reu Junqueira, J. Deciphering public voices in the digital era: benchmarking ChatGPT for analyzing citizen feedback in Hamilton, New Zealand. J. Am. Plann. Assoc. 90, 728–741 (2024).

    Article  Google Scholar 

  29. Wu, T. et al. A brief overview of ChatGPT: the history, status quo and potential future development. IEEE/CAA J. Autom. Sin. 10, 1122–1136 (2023).

    Article  Google Scholar 

  30. Vaswani, A. et al. Attention is all you need. In Advances in Neural Information Processing Systems 30 (eds von Luxburg, U. et al.) 5999–6009 (Neural Information Processing Systems Foundation, 2017)

  31. Tang, R., Chuang, Y.-N. & Hu, X. The science of detecting LLM-generated text. Commun. ACM 67, 50–59 (2024).

    Article  Google Scholar 

  32. OpenAI et al. GPT-4 technical report. Preprint at https://doi.org/10.48550/arXiv.2303.08774 (2023)

  33. Zheng, L. et al. Judging LLM-as-a-judge with MT-bench and Chatbot Arena. Adv. Neural Inf. Process. Syst. 36, 46595–46623 (2023).

    Google Scholar 

  34. Brown, T. B. et al. Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 33, 1877–1901 (2020).

    Google Scholar 

  35. Batty, M. A new kind of search. Environ. Plan. B Urban Anal. City Sci. 50, 575–578 (2023).

    Article  Google Scholar 

  36. Poirier, L. et al. Making plans findable, accessible, interoperable, and reusable with data infrastructure: a search engine for constructing, analyzing, and visualizing planning documents. Environ. Plan. B Urban Anal. City Sci. https://doi.org/10.1177/23998083241227471 (2024)

  37. Fu, X., Li, C. & Zhai, W. Using natural language processing to read plans: a study of 78 resilience plans from the 100 resilient cities network. J. Am. Plann. Assoc. 89, 107–119 (2023).

    Article  Google Scholar 

  38. Alexander, E. R. Rationality revisited: planning paradigms in a post-postmodernist perspective. J. Plan. Educ. Res. 19, 242–256 (2000).

    Article  Google Scholar 

  39. Friedmann, J. The future of comprehensive urban planning: a critique. Public Adm. Rev. 31, 315–326 (1971).

    Article  Google Scholar 

  40. Berke, P. et al. Evaluation of networks of plans and vulnerability to hazards and climate change: a resilience scorecard. J. Am. Plann. Assoc. 81, 287–302 (2015).

    Article  Google Scholar 

  41. Senadheera, S. et al. Understanding chatbot adoption in local governments: a review and framework. J. Urban Technol. https://doi.org/10.1080/10630732.2023.2297665 (2024)

  42. Forsyth, A. Theories and planning theories. J. Am. Plann. Assoc. 87, 155–158 (2021).

    Article  Google Scholar 

  43. Bersenev, D., Yachie-Kinoshita, A. & Palaniappan, S. K. Replicating a high-impact scientific publication using systems of large language models. Preprint at bioRxiv https://doi.org/10.1101/2024.04.08.588614 (2024)

  44. Sun, C., Huang, S. & Pompili, D. LLM-based multi-agent reinforcement learning: current and future directions. Preprint at https://doi.org/10.48550/arXiv.2405.11106 (2024)

  45. Hao, H., Wang, Y. & Chen, J. Empowering scenario planning with artificial intelligence: a perspective on building smart and resilient cities. Engineering 43, 272–283 (2024).

    Article  Google Scholar 

  46. Chakraborty, A. & McMillan, A. Scenario planning for urban planners: toward a practitioner’s guide. J. Am. Plann. Assoc. 81, 18–29 (2015).

    Article  Google Scholar 

  47. Watson, V. Conflicting rationalities: implications for planning theory and ethics. Plan. Theory Pract. 4, 395–407 (2003).

    Article  Google Scholar 

  48. Silver, D. et al. Mastering the game of Go without human knowledge. Nature 550, 354–359 (2017).

    Article  Google Scholar 

  49. Batty, M. Digital twins. Environ. Plan. B Urban Anal. City Sci. 45, 817–820 (2018).

    Article  Google Scholar 

  50. Yigitcanlar, T., Degirmenci, K., Butler, L. & Desouza, K. C. What are the key factors affecting smart city transformation readiness? Evidence from Australian cities. Cities 120, 103434 (2022).

    Article  Google Scholar 

  51. Ziems, C. et al. Can large language models transform computational social science? Comput. Linguist. 50, 237–291 (2024).

    Article  Google Scholar 

  52. Yu, S., Brand, A. D. & Berke, P. Making room for the river: applying a plan integration for resilience scorecard to a network of plans in Nijmegen, The Netherlands. J. Am. Plann. Assoc. 86, 417–430 (2020).

    Article  Google Scholar 

  53. Liu, N. F. et al. Lost in the middle: how language models use long contexts. Trans. Assoc. Comput. Linguist. 12, 157–173 (2024).

    Article  Google Scholar 

  54. Gao, Y. et al. Retrieval-augmented generation for large language models: a survey. Preprint at https://doi.org/10.48550/arXiv.2312.10997 (2023)

  55. Edge, D. et al. From local to global: a graph RAG approach to query-focused summarization. Preprint at https://doi.org/10.48550/arXiv.2404.16130 (2024)

  56. Vonk, G., Geertman, S. & Schot, P. Bottlenecks blocking widespread usage of planning support systems. Environ. Plan. A 37, 909–924 (2005).

    Article  Google Scholar 

  57. Sanchez, T. W., Brenman, M. & Ye, X. The ethical concerns of artificial intelligence in urban planning. J. Am. Plann. Assoc. 91, 294–307 (2024).

    Article  Google Scholar 

  58. Daniel, C., Wentz, E., Hurtado, P., Yang, W. & Pettit, C. Digital technology use and future expectations: a multinational survey of professional planners. J. Am. Plann. Assoc. 90, 405–420 (2024).

    Article  Google Scholar 

  59. Humlum, A. & Vestergaard, E. The unequal adoption of ChatGPT exacerbates existing inequalities among workers. Proc. Natl Acad. Sci. USA 122, e2414972121 (2025).

    Article  Google Scholar 

Download references

Acknowledgements

We thank A. Forsyth from Harvard University for her valuable comments on the early draft of this Perspective.

Author information

Author notes

  1. These authors contributed equally: Xinyu Fu, Chaosu Li.

Authors and Affiliations

  1. Environmental Planning Program, University of Waikato, Hamilton, New Zealand

    Xinyu Fu

  2. Urban Governance and Design Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China

    Chaosu Li

  3. Environmental Planning Institute, Graduate School of Environmental Studies, Seoul National University, Seoul, South Korea

    Steven Jige Quan

  4. Graduate School of Environmental Studies, Seoul National University, Seoul, South Korea

    Steven Jige Quan

  5. City 4.0 Lab, School of Architecture and Built Environment, Queensland University of Technology, Brisbane, Queensland, Australia

    Tan Yigitcanlar

  6. Civic Analytics Discipline, Alta Planning + Design, Seattle, WA, USA

    David Wasserman

Authors
  1. Xinyu Fu
    View author publications

    Search author on:PubMed Google Scholar

  2. Chaosu Li
    View author publications

    Search author on:PubMed Google Scholar

  3. Steven Jige Quan
    View author publications

    Search author on:PubMed Google Scholar

  4. Tan Yigitcanlar
    View author publications

    Search author on:PubMed Google Scholar

  5. David Wasserman
    View author publications

    Search author on:PubMed Google Scholar

Contributions

X.F. conceived the idea for the Perspective and drafted the initial manuscript. X.F. and C.L. jointly reviewed the relevant literature, synthesized key insights and refined the core arguments. X.F., C.L. and S.J.Q. provided critical revisions and contributed to the final editing. T.Y. and D.W. contributed to refining the initial submission and revisions.

Corresponding author

Correspondence to Xinyu Fu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Cities thanks Dongjie Wang and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Fu, X., Li, C., Quan, S.J. et al. Large language models in urban planning. Nat Cities 2, 585–592 (2025). https://doi.org/10.1038/s44284-025-00261-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s44284-025-00261-7

This article is cited by

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing