Search

Menu
Search
in Ecology

Unsupervised mapping of urban tree diversity using spatially-aware visual clustering

140 Views


Abstract

Urban tree biodiversity is critical for climate resilience, ecological stability, and livability in cities, yet most municipalities lack detailed knowledge of their canopies. Field-based inventories provide reliable estimates of Shannon and Simpson diversity but are costly and time-consuming, while supervised AI methods require labeled data that often fail to generalize across regions. We introduce an unsupervised clustering framework that integrates visual embeddings from street-level imagery with spatial planting patterns to estimate biodiversity without labels. Applied to eight North American cities, the method recovers genus-level diversity patterns with high fidelity, achieving low Wasserstein distances to ground truth for Shannon and Simpson indices and preserving spatial autocorrelation. This scalable, fine-grained approach enables biodiversity mapping in cities lacking detailed inventories and offers a pathway for continuous, low-cost monitoring to support equitable access to greenery and adaptive management of urban ecosystems.

Data availability

All data supporting the findings of this study are available within the paper and its supplementary information. The code used for analysis is available at https://github.com/Diaa340/Releaf/.

References

  1. Magurran, A.E. Diversity indices and species abundance models. In: Ecological Diversity and Its Measurement, (Ed. Magurran, A.E.) pp. 7–45. https://doi.org/10.1007/978-94-015-7358-0_2 (Springer, Dordrecht, 1988).

  2. Magurran, A.E. Choosing and interpreting diversity measures. In: Ecological Diversity and Its Measurement, (Ed. Magurran, A.E.) pp. 61–80. https://doi.org/10.1007/978-94-015-7358-0_4 (Springer, Dordrecht, 1988).

  3. Nielsen, A. B., Östberg, J. & Delshammar, T. Review of urban tree inventory methods used to collect data at single-tree level. Arboric. Urban For. (AUF) 40(2), 96–111 (2014).

    Google Scholar 

  4. Davies, Z. G., Edmondson, J. L., Heinemeyer, A., Leake, J. R. & Gaston, K. J. Mapping an urban ecosystem service: quantifying above-ground carbon storage at a city-wide scale. J. Appl. Ecol. 48(5), 1125–1134 (2011).

    Google Scholar 

  5. Escobedo, F. & Seitz, J. Costs of managing an Urban Forest. EDIS 2009(7) https://doi.org/10.32473/edis-fr279-2009 (2009).

  6. Boonman, C. C. F. et al. More than 17,000 tree species are at risk from rapid global change. Nat. Commun. 15(1), 166. https://doi.org/10.1038/s41467-023-44321-9 (2024) (Publisher: Nature Publishing Group).

    Google Scholar 

  7. Cardinale, B. J. et al. Biodiversity loss and its impact on humanity. Nature 486(7401), 59–67. https://doi.org/10.1038/nature11148 (2012) (Publisher: Nature Publishing Group).

    Google Scholar 

  8. Paul, B. The scale of the biodiversity crisis laid bare. Nature 635, 31 (2024).

    Google Scholar 

  9. …Aronson, M. F. J. et al. A global analysis of the impacts of urbanization on bird and plant diversity reveals key anthropogenic drivers. Proc. R. Soc. B: Biol. Sci. 281(1780), 20133330. https://doi.org/10.1098/rspb.2013.3330 (2014) (Publisher: Royal Society).

    Google Scholar 

  10. Helden, A. J., Stamp, G. C. & Leather, S. R. Urban biodiversity: comparison of insect assemblages on native and non-native trees. Urban Ecosyst. 15(3), 611–624. https://doi.org/10.1007/s11252-012-0231-x (2012).

    Google Scholar 

  11. Gunnarsson, B., Knez, I., Hedblom, M. & Sang, A. O. Effects of biodiversity and environment-related attitude on perception of urban green space. Urban Ecosyst. 20(1), 37–49. https://doi.org/10.1007/s11252-016-0581-x (2017).

    Google Scholar 

  12. Lin, B. B., Fuller, R. A., Bush, R., Gaston, K. J. & Shanahan, D. F. Opportunity or Orientation? Who Uses Urban Parks and Why. PLOS ONE 9(1), 87422. https://doi.org/10.1371/journal.pone.0087422. (2014) (Publisher: Public Library of Science).

    Google Scholar 

  13. Liu, J. & Slik, F. Are street trees friendly to biodiversity?. Landsc. Urban Plan. 218, 104304. https://doi.org/10.1016/j.landurbplan.2021.104304 (2022).

    Google Scholar 

  14. Hewitt, C. N., Ashworth, K. & MacKenzie, A. R. Using green infrastructure to improve urban air quality (GI4AQ). Ambio 49(1), 62–73. https://doi.org/10.1007/s13280-019-01164-3 (2020).

    Google Scholar 

  15. McPherson, E. G., Doorn, N. & Goede, J. Structure, function and value of street trees in California, USA. Urban For. Urban Green. 17, 104–115. https://doi.org/10.1016/j.ufug.2016.03.013 (2016).

    Google Scholar 

  16. Wang, X., Dallimer, M., Scott, C. E., Shi, W. & Gao, J. Tree species richness and diversity predicts the magnitude of urban heat island mitigation effects of greenspaces. Sci. Total Environ. 770, 145211. https://doi.org/10.1016/j.scitotenv.2021.145211 (2021).

    Google Scholar 

  17. Ishimatsu, K., Ito, K. & Mitani, Y. Developing urban green spaces and effective use of rooftop spaces for cooling and urban biodiversity. In: Urban Biodiversity and Ecological Design for Sustainable Cities (Ed. Ito, K.), pp. 217–240. https://doi.org/10.1007/978-4-431-56856-8_10 (Springer, Tokyo, 2021).

  18. Zhao, J., Xu, W. & Li, R. Visual preference of trees: The effects of tree attributes and seasons. Urban For. Urban Green. 25, 19–25. https://doi.org/10.1016/j.ufug.2017.04.015 (2017).

    Google Scholar 

  19. Muluneh, M. G. & Worku, B. B. Contributions of urban green spaces for climate change mitigation and biodiversity conservation in Dessie city. Northeastern Ethiopia. Urban Climate 46, 101294. https://doi.org/10.1016/j.uclim.2022.101294 (2022).

    Google Scholar 

  20. Esperon-Rodriguez, M. et al. Climate change increases global risk to urban forests. Nat. Clim. Change 12(10), 950–955. https://doi.org/10.1038/s41558-022-01465-8 (2022) (Publisher: Nature Publishing Group).

    Google Scholar 

  21. Jenerette, G. D. et al. Climate tolerances and trait choices shape continental patterns of urban tree biodiversity. Glob. Ecol. Biogeogr. 25(11), 1367–1376. https://doi.org/10.1111/geb.12499 (2016) (Publisher: John Wiley & Sons Ltd).

    Google Scholar 

  22. Beery, S.M. Where the Wild Things Are: Computer Vision for Global-Scale Biodiversity Monitoring. Ph.D., California Institute of Technology, United States – California https://doi.org/10.7907/m4mt-2q51 . ISBN: 9798380870627. https://www.proquest.com/docview/2898870216/abstract/D69C70D751F84DC2PQ/1 (2023).

  23. Stevens, S. et al. Bioclip: A vision foundation model for the tree of life. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 19412–19424 (2024).

  24. Sastry, S., Khanal, S., Dhakal, A., Ahmad, A. & Jacobs, N. Taxabind: A unified embedding space for ecological applications. In: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1765–1774 (IEEE, 2025).

  25. Sierra, E., Gillespie, L.E., Soltani, S., Exposito-Alonso, M. & Kattenborn, T. Divshift: Exploring domain-specific distribution shifts in large-scale, volunteer-collected biodiversity datasets. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 28386–28396 (2025).

  26. Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597–1607 (PmLR, 2020).

  27. Haukoos, J. S. & Lewis, R. J. Advanced statistics: bootstrapping confidence intervals for statistics with “difficult’’ distributions. Acad. Emerg. Med. 12(4), 360–365 (2005).

    Google Scholar 

  28. Li, T. et al. Targeted supervised contrastive learning for long-tailed recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6918–6928 (2022).

  29. Bhat, S.D., More, A., Soni, M. & Agrawal, S. Prior2posterior: Model prior correction for long-tailed learning. In: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1289–1298 (IEEE, 2025).

  30. Liu, J., Sun, Y., Han, C., Dou, Z. & Li, W. Deep representation learning on long-tailed data: A learnable embedding augmentation perspective. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2970–2979 (2020)

  31. Panaretos, V. M. & Zemel, Y. Statistical aspects of wasserstein distances. Annu. Rev. Stat. Appl. 6(1), 405–431. https://doi.org/10.1146/annurev-statistics-030718-104938 (2019).

    Google Scholar 

  32. Jost, L. Entropy and diversity. Oikos 113(2), 363–375 (2006).

    Google Scholar 

  33. Panaretos, V.M. & Zemel, Y. An Invitation to Statistics in Wasserstein Space. Briefs in Probability and Mathematical Statistics. 1st edn. https://doi.org/10.1007/978-3-030-38438-8 (Springer Springer, Cham, 2020).

  34. House of Commons Standing Committee on Access to Information, Privacy and Ethics. Mapping Privacy Protection in the Digital World: Study of the Privacy Implications of Street-Level Imaging Applications. Parliament of Canada (2011).

  35. Metzler, A. B. et al. Unsupervised deep clustering of high-resolution satellite imagery reveals phenotypes of urban development in sub-saharan africa. Sci. Total Environ. 988, 179739 (2025).

    Google Scholar 

  36. Wang, S., Azzari, G. & Lobell, D. B. Crop type mapping without field-level labels: Random forest transfer and unsupervised clustering techniques. Remote Sens. Environ. 222, 303–317. https://doi.org/10.1016/j.rse.2018.12.026 (2019).

    Google Scholar 

  37. Saha, O., Van Horn, G. & Maji, S. Improved zero-shot classification by adapting vlms with text descriptions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 17542–17552 (2024).

  38. Beery, S. et al. The Auto Arborist Dataset: A Large-Scale Benchmark for Multiview Urban Forest Monitoring Under Domain Shift. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21262–21275. https://doi.org/10.1109/CVPR52688.2022.02061 . https://ieeexplore.ieee.org/document/9878589/ (IEEE, New Orleans, LA, USA, 2022).

  39. Wegner, J.D., Branson, S., Hall, D., Schindler, K. & Perona, P. Cataloging Public Objects Using Aerial and Street-Level Images – Urban Trees. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6014–6023. https://doi.org/10.1109/CVPR.2016.647. http://ieeexplore.ieee.org/document/7781016/ (IEEE, Las Vegas, NV, USA, 2016).

  40. Brown, C.F. etal. AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data arXiv:2507.22291 (2025).

  41. Barbier, S., Chevalier, R., Loussot, P., Bergès, L. & Gosselin, F. Improving biodiversity indicators of sustainable forest management: Tree genus abundance rather than tree genus richness and dominance for understory vegetation in french lowland oak hornbeam forests. For. Ecol. Manag. 258, 176–186 (2009).

    Google Scholar 

  42. Sjöman, H., Östberg, J. & Bühler, O. Diversity and distribution of the urban tree population in ten major nordic cities. Urban For. Urban Green. 11(1), 31–39 (2012).

    Google Scholar 

  43. Nowak, D. J., Greenfield, E. J., Hoehn, R. E. & Lapoint, E. Carbon storage and sequestration by trees in urban and community areas of the united states. Environ. Pollut. 178, 229–236 (2013).

    Google Scholar 

  44. Mattocks, R. H. Street Trees: Their Selection, Planting and After-Care: Illustrated. Town Plan. Rev. 11(1), 21. https://doi.org/10.3828/tpr.11.1.u56t446671022x19 (1924).

    Google Scholar 

  45. Ankerst, M., Breunig, M. M., Kriegel, H.-P. & Sander, J. OPTICS: ordering points to identify the clustering structure. Proc. ACM SIGMOD Int. Conf. Manag. Data 28, 49–60 (1999).

  46. Bezdek, J. C., Ehrlich, R. & Full, W. FCM: The fuzzy c-means clustering algorithm. Computers & geosciences 10(2–3), 191–203 (1984) (ISBN: 0098-3004 Publisher: Elsevier).

    Google Scholar 

  47. Bhattacharjee, P. & Mitra, P. A survey of density based clustering algorithms. Front. Comput. Sci. 15(1), 151308 (2021).

    Google Scholar 

  48. McInnes, L. et al. hdbscan: Hierarchical density based clustering. J. Open Source Softw. 2(11), 205 (2017).

    Google Scholar 

  49. Xia, P., Zhang, L. & Li, F. Learning similarity with cosine similarity ensemble. Inf. Sci. 307, 39–52 (2015).

    Google Scholar 

Download references

Acknowledgements

The authors thank Dubai Future Foundation, UnipolTech, Consiglio per la Ricerca in Agricoltura e l’Analisi dell’Economia Agraria, Volkswagen Group America, FAE Technology, Samoo Architects & Engineers, Shell, GoAigua, ENEL Foundation, Kyoto University, Weizmann Institute of Science, Universidad Autónoma de Occidente, Instituto Politecnico Nacional, Imperial College London, Universitá di Pisa, KTH Royal Institute of Technology, AMS Institute and all the members of the MIT Senseable City Lab Consortium for supporting this research. This work was supported by the Open Access Program from the American University of Sharjah, UAE.

Funding

This research received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors.

Author information

Authors and Affiliations

  1. Department of Urban Studies and Planning, Senseable City Laboratory, Massachusetts Institute of Technology, 77 Massachusetts Ave, Cambridge, MA 02139, Massachusetts, USA

    Diaa Addeen Abuhani, Marco Seccaroni, Martina Mazzarello, Fabio Duarte & Carlo Ratti

  2. Department of Computer Science and Engineering, American University of Sharjah, 127 Street, University City, 26666, Sharjah, UAE

    Diaa Addeen Abuhani & Imran Zualkernan

  3. Department of Architecture, Built Environment, and Construction Engineering, Politecnico di Milano, Piazza Leonardo da Vinci, 32, Milano, 20133, Milan, Italy

    Marco Seccaroni & Carlo Ratti

Authors

  1. Diaa Addeen Abuhani
    View author publications

    Search author on:PubMed Google Scholar

  2. Marco Seccaroni
    View author publications

    Search author on:PubMed Google Scholar

  3. Martina Mazzarello
    View author publications

    Search author on:PubMed Google Scholar

  4. Imran Zualkernan
    View author publications

    Search author on:PubMed Google Scholar

  5. Fabio Duarte
    View author publications

    Search author on:PubMed Google Scholar

  6. Carlo Ratti
    View author publications

    Search author on:PubMed Google Scholar

Contributions

M.M., F.D., I.Z., M.S., and D.A.A. conceptualized the study. D.A.A. and M.S. performed the methodology development and data curation, conducted the formal analysis, and wrote the original draft. M.M., F.D., and I.Z. supervised the research, C.R. provided resources, and handled funding acquisition. All authors reviewed and edited the manuscript. This paper represents the opinions of the author(s) and does not mean to represent the position or opinions of the American University of Sharjah.

Corresponding authors

Correspondence to
Diaa Addeen Abuhani or Martina Mazzarello.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethics approval and consent to participate

Not applicable.

Consent for publication

Not applicable.

Additional information

Publisher’s note

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

Supplementary Information

Supplementary Information.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Reprints and permissions

About this article

Cite this article

Abuhani, D.A., Seccaroni, M., Mazzarello, M. et al. Unsupervised mapping of urban tree diversity using spatially-aware visual clustering.
Sci Rep (2026). https://doi.org/10.1038/s41598-026-37043-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1038/s41598-026-37043-7

Keywords

  • Biodiversity
  • Unsupervised Learning
  • Clustering
  • Streetviews

Source: Ecology - nature.com

A probabilistic approach to predicting alfalfa’s winter survival using local conditions, weather and management factors

Wetland water quality status and suitability for human intended uses in Angolelana Tara District, North Shewa Zone, Central Ethiopia

This portal is not a newspaper as it is updated without periodicity. It cannot be considered an editorial product pursuant to law n. 62 of 7.03.2001. The author of the portal is not responsible for the content of comments to posts, the content of the linked sites. Some texts or images included in this portal are taken from the internet and, therefore, considered to be in the public domain; if their publication is violated, the copyright will be promptly communicated via e-mail. They will be immediately removed.

Back to Top
Close