Detection and clustering of urban form types with machine learning: insights into Thessaloniki's urban planning and evolution

Abstract

Advances in Machine learning open new frontiers in the systematic analysis of urban form. The study presents a scalable and interpretable framework that derives an urban-form typology by performing unsupervised clustering of 17 multi-scale morphological indicators encoded at the cadastral plot scale. The method adds positional information with the Getis-Ord Gi* spatial autocorrelation metric to encourage spatially homogeneous clusters. The study employs a combination of UMAP for non-linear dimensionality reduction and BIRCH for scalable clustering. Caveats of using the plot as a spatial unit are mitigated via filtering, tessellation and buffering. Applied to the metropolitan area of Thessaloniki, Greece, the framework identifies 14 urban form types organized into five families with similar characteristics. The resulting typology reveals, in a Conzenian fashion, patterns of urban development rooted in the city’s modern history. Results are validated quantitatively with performance metrics and qualitatively using aerial imagery and established knowledge of Thessaloniki’s planning and evolution.

Keywords

Urban form / Clustering / UMAP / BIRCH / Machine learning / Cadastral plot

References

[1] Ahn H, Lee J, Hong A. Urban form and air pollution: Clustering patterns of urban form factors related to particulate matter in Seoul, Korea. Sustainable Cities and Society, 2022, 81. 103859

[2] Alexander C, Ishikawa S, Silverstein MA Pattern Language: Towns, 1977Oxford University Press.

[3] Bastéa E, Hastaoglou-Martinidis VUrban change and the persistence of memory in modern Thessaloniki, 2020Routledge.

[4] Battey CJ, Coffing GC, Kern AD. Visualizing population structure with variational autoencoders. G3 Genes|genomes|genetics, 2021, 11(1. jkaa036

[5] Batty MScience in Planning: Theory, 2018Routledge

[6] Batty M. Urban analytics defined. Environment and Planning b: Urban Analytics and City Science, 2019, 46(3): 403-405.

[7] Berghauser Pont, M., & Haupt, P. (2023). Spacematrix: Space, Density and Urban Form - revised edition. In TU Delft OPEN Books. TU Delft OPEN Books. https://doi.org/10.59490/mg.38

[8] Bobkova E, Berghauser Pont M, Marcus L. Towards analytical typologies of plot systems: Quantitative profile of five European cities. Environment and Planning b: Urban Analytics and City Science, 2021, 48(4): 604-620.

[9] Boeing G. OSMnx: New methods for acquiring, constructing, analyzing, and visualizing complex street networks. Computers, Environment and Urban Systems, 2017, 65: 126-139.

[10] Boeing G, Higgs C, Liu S, Giles-Corti B, Sallis JF, Cerin E, Lowe M, Adlakha D, Hinckson E, Moudon AV, Salvo D, Adams MA, Barrozo LV, Bozovic T, Delclòs-Alió X, Dygrýn J, Ferguson S, Gebel K, Ho TP, Lai P-C, Martori JC, Nitvimol K, Queralt A, Roberts JD, Sambo GH, Schipperijn J, Vale D, Van de Weghe N, Vich G, Arundel J. Using open data and open-source software to develop spatial indicators of urban design and transport features for achieving healthy and sustainable cities. The Lancet Global Health, 2022, 10(6): e907-e918.

[11] Bruyns, G. J., Higgins, C. D., & Nel, D. H. (2020). Urban volumetrics: From vertical to volumetric urbanisation and its extensions to empirical morphological analysis. Urban Studies, 58(5), 922–940. https://doi.org/10.1177/0042098020936970

[12] Campello, R. J. G. B., Moulavi, D., & Sander, J. (2013). Density-Based Clustering Based on Hierarchical Density Estimates. In J. Pei, V. S. Tseng, L. Cao, H. Motoda, & G. Xu (Eds.), Advances in Knowledge Discovery and Data Mining (pp. 160–172). Springer. https://doi.org/10.1007/978-3-642-37456-2_14

[13] Caniggia, G. (1963). Lettura di una città. Centro Studi di Storia Urbanistica.

[14] Chen C-Y, Koch F, Reicher C. Developing a two-level machine-learning approach for classifying urban form for an East Asian mega-city. Environment and Planning b: Urban Analytics and City Science, 2023, 51(4): 854-869.

[15] Conzen MRGThinking about Urban Form: Papers on Urban Morphology, 1932–1998, 2004Peter Lang

[16] Cullen GConcise Townscape, 1961Routledge

[17] Debray H, Gassilloud M, Lemoine-Rodríguez R, Wurm M, Zhu X, Taubenböck H. Universal patterns of intra-urban morphology: Defining a global typology of the urban fabric using unsupervised clustering. International Journal of Applied Earth Observation and Geoinformation, 2025, 141. 104610

[18] Dibble, J., Prelorendjos, A., Romice, O., Zanella, M., Strano, E., Pagel, M., & Porta, S. (2015). Urban Morphometrics: Towards a Science of Urban Evolution (arXiv:1506.04875). arXiv. https://doi.org/10.48550/arXiv.1506.04875

[19] Dibble J, Prelorendjos A, Romice O, Zanella M, Strano E, Pagel M, Porta S. On the origin of spaces: Morphometric foundations of urban form evolution. Environment and Planning b: Urban Analytics and City Science, 2019, 46(4): 707-730.

[20] Duque JC, Aldstadt J, Velasquez E, Franco JL, Betancourt A. A computationally efficient method for delineating irregularly shaped spatial clusters. Journal of Geographical Systems, 2011, 13(4): 355-372.

[21] EC. (2023). GHSL Data Package R2023. https://human-settlement.emergency.copernicus.eu/

[22] EC. (2024). Normalised Difference Vegetation Index 2016-present (raster 10 m), Europe, daily. https://land.copernicus.eu/en/products/vegetation/high-resolution-normalised-difference-vegetation-index

[23] EC. (2025). Copernicus. https://www.copernicus.eu/

[24] EEA. (2016). European Digital Elevation Model (EU-DEM). https://www.eea.europa.eu/en/datahub/datahubitem-view/d08852bc-7b5f-4835-a776-08362e2fbf4b

[25] Efeoglu HE, Joutsiniemi A, Mozuriunaite S. Exploring the plot patterns of the retail landscape: The case of the Helsinki Metropolitan area. Environment and Planning b: Urban Analytics and City Science, 2024, 51(6): 1210-1226.

[26] eKathimerini. (2025). Over 14,000 sign petition to turn TIF site into park. https://www.ekathimerini.com/in-depth/society-in-depth/1270502/over-14000-sign-petition-to-turn-tif-site-into-park/

[27] El-Ashmawy KLA. Testing the positional accuracy of OpenStreetMap data for mapping applications. Geodesy and Cartography, 2016, 42(1): 25-30.

[28] ELSTAT. (2011). ELSTAT 2011 Census data . https://www.statistics.gr/en/statistical-data-request.

[29] Fang Z, Jin Y, Zheng S, Zhao L, Yang T. UrbanClassifier: A deep learning-based model for automated typology and temporal analysis of urban fabric across multiple spatial scales and viewpoints. Computers, Environment and Urban Systems, 2024, 111. 102132

[30] Fleischmann M. Momepy: Urban morphology measuring toolkit. Journal of Open Source Software, 2019, 4(43. 1807

[31] Fleischmann M, Arribas-Bel D. Geographical characterisation of British urban form and function using the spatial signatures framework. Scientific Data, 2022, 9(1): 546.

[32] Fleischmann M, Feliciotti A, Romice O, Porta S. Morphological tessellation as a way of partitioning space: Improving consistency in urban morphology at the plot scale. Computers, Environment and Urban Systems, 2020, 80. 101441

[33] Fleischmann M, Feliciotti A, Romice O, Porta S. Methodological foundation of a numerical taxonomy of urban form. Environment and Planning b: Urban Analytics and City Science, 2022, 49(4): 1283-1299.

[34] Fleischmann M, Romice O, Porta S. Measuring urban form: Overcoming terminological inconsistencies for a quantitative and comprehensive morphologic analysis of cities. Environment and Planning b: Urban Analytics and City Science, 2021, 48(8): 2133-2150.

[35] Gemenetzi G. Thessaloniki: The changing geography of the city and the role of spatial planning. Cities, 2017, 64: 88-97.

[36] Giannaros TM, Melas D. Study of the urban heat island in a coastal Mediterranean city: The case study of Thessaloniki, Greece. Atmospheric Research, 2012, 118: 103-120.

[37] Goerlich Gisbert FJ, Cantarino Martí I, Gielen E. Clustering cities through urban metrics analysis. Journal of Urban Design, 2017, 22(5): 689-708.

[38] Hellenic Cadastre. (2025, January 18). Aerial Photos Viewing Service [Online service]. http://gis.ktimanet.gr/wms/ktbasemap/default.aspx

[39] HC. (2024, August 15). Download service (WFS) for the land plots of the public legal entity “Hellenic Cadastre.”https://data.ktimatologio.gr/dataset/27a9e70e-5232-485d-b407-c89e9d45c6b6

[40] Hsu, Y. Y., & Han, H. (2024). Toward volumetric urbanism: Analysing the spatial-temporal dynamics of 3D floor space use in the built environment. Environment and Planning B: Urban Analytics and City Science, 52(5), 1181–1196. https://doi.org/10.1177/23998083241286592

[41] Iungman T, Khomenko S, Barboza EP, Cirach M, Gonçalves K, Petrone P, Erbertseder T, Taubenböck H, Chakraborty T, Nieuwenhuijsen M. The impact of urban configuration types on urban heat islands, air pollution, CO2 emissions, and mortality in Europe: A data science approach. The Lancet Planetary Health, 2024, 8(7): e489-e505.

[42] Jang KM, Suh H, Haddad FG, Sun M, Duarte F, Kim Y. Urban street clusters: Unraveling the associations of street characteristics on urban vibrancy dynamics in age, time, and day. Urban Informatics, 2024, 3(1): 27.

[43] Jolliffe IT, Cadima J. Principal component analysis: A review and recent developments. Philosophical Transactions of the Royal Society a: Mathematical, Physical and Engineering Sciences, 2016, 374(2065): 20150202.

[44] Joshi MY, Rodler A, Musy M, Guernouti S, Cools M, Teller J. Identifying urban morphological archetypes for microclimate studies using a clustering approach. Building and Environment, 2022, 224. 109574

[45] Kalogirou, N. (with Dousi, M., Kontaxakis, D., Kotsopoulos, S., & Tzonis, A.). (2021). The Palimpsest of Aristotelous: Byzantine visions and eclectic localism. University Studio Press.

[46] Karagianni, M. (2022). Making Thessaloniki Resilient? The Enclosing Process of the Urban Green Commons. Urban Planning, 8(1). https://doi.org/10.17645/up.v8i1.5990

[47] K-Architects. (2025). Allatini project—Urban planning of the Allatini Kerameia Property: Architectural analysis for a high-rise building. K-Architects. https://www.kotsiopoulos-architects.gr/allatini-project

[48] Kopczewska K. Spatial machine learning: New opportunities for regional science. The Annals of Regional Science, 2022, 68(3): 713-755.

[49] Kropf KThe Handbook of Urban Morphology, 2017Wiley.

[50] Lagopoulos APh. Monumental urban space and national identity: The early twentieth century new plan of Thessaloniki. Journal of Historical Geography, 2005, 31(1): 61-77.

[51] Lambrianidis, L., Hatziprokopiou, P., Pratsinakis, M., & Vogiatzis, N. (2008). Thessaloniki City Report (1st Phase of the GEITONIES Research Project, European Commission Research DG, 7th Framework Programme). European Commission. https://www.researchgate.net/publication/241889398_Thessaloniki_city_report

[52] Lang J. International urban design: Theory and practice. Urban Design and Planning, 2009, 162(1): 7-17.

[53] Latinopoulos D. Evaluating the importance of urban green spaces: A spatial analysis of citizens’ perceptions in Thessaloniki. Euro-Mediterranean Journal for Environmental Integration, 2022, 7(2): 299-308.

[54] Leontidou, L. (1990). The Mediterranean City in Transition: Social change and urban development. Cambridge University Press.

[55] Li N, Quan SJ. Identifying urban form typologies in Seoul using a new Gaussian mixture model-based clustering framework. Environment and Planning b: Urban Analytics and City Science, 2023, 50(9): 2342-2358.

[56] Liu Y, Jun E, Li Q, Heer J. Latent space cartography: Visual analysis of vector space embeddings. Computer Graphics Forum, 2019, 38(3): 67-78.

[57] Lynch KThe image of the city, 1960MIT Press

[58] Lynch, K. (1984). Good city form. In City. MIT Press. http://www.amazon.co.uk/Good-City-Form-K-Lynch/dp/0262620464

[59] Ma H, Li J, Ye X. Deep learning meets urban design: Assessing streetscape aesthetic and design quality through AI and cluster analysis. Cities, 2025, 162. 105939

[60] Ma R, Li X, Chen J. An elastic urban morpho-blocks (EUM) modeling method for urban building morphological analysis and feature clustering. Building and Environment, 2021, 192. 107646

[61] Martin, L., & March, L. (1972). Urban Space and Structures (L. Martin & L. March, Eds.). Cambridge University Press.

[62] McInnes, L. (2018). UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction—Umap 0.5 documentation. https://umap-learn.readthedocs.io/en/latest/

[63] McInnes, L., Healy, J., & Melville, J. (2020). UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction (arXiv:1802.03426). arXiv. https://doi.org/10.48550/arXiv.1802.03426

[64] Medcruise. (2025, February 20). ThPA S.A.: Approval for the Master Plan for the Port of Thessaloniki through the issuance of a relevant Presidential Decree. MedCruise. https://www.medcruise.com/news/thpa-s-a-approval-for-the-master-plan-for-the-port-of-thessaloniki-through-the-issuance-of-a-relevant-presidential-decree

[65] Mondal R, Ignatova E, Walke D, Broneske D, Saake G, Heyer R. Clustering graph data: The roadmap to spectral techniques. Discover Artificial Intelligence, 2024, 4(1): 7.

[66] Moosavi, V. (2017). Urban morphology meets deep learning: Exploring urban forms in one million cities, town and villages across the planet. 1–10.

[67] Moudon AVFranck KA, Schneekloth LH. Getting to know the built landscape: Typomorphology. Ordering Space: Types in Architecture and Design, 1994Van Nostrand Reinhold289-311

[68] Moussiopoulos Ν, Vlachokostas Ch, Tsilingiridis G, Douros I, Hourdakis E, Naneris C, Sidiropoulos C. Air quality status in Greater Thessaloniki Area and the emission reductions needed for attaining the EU air quality legislation. Science of the Total Environment, 2009, 407(4): 1268-1285.

[69] Muratori, S. (1959). Studi per una operante storia urbana di Venezia,. Instituto Poligrafico dello Stato.

[70] Nielsen F. On the Jensen-shannon symmetrization of distances relying on abstract means. Entropy, 2019.

[71] Norberg-Schulz, C. (1980). Genius loci: Towards a phenomenology of architecture. Rizzoli. http://archive.org/details/geniuslocitoward0000norb

[72] Oikonomou, M., & Christodoulou, C. (2022). Evolution and transformation processes of urban form: Urban tissues in Thessaloniki, Greece. Conference Proceedings – XXIX International Seminar on Urban Form ISUF 2022: Urban Redevelopment and Revitalisation. A Multidisciplinary Perspective. https://doi.org/10.34658/9788367934039.98

[73] Oke JB, Aboutaleb YM, Akkinepally A, Azevedo CL, Han Y, Zegras PC, Ferreira J, Ben-Akiva ME. A novel global urban typology framework for sustainable mobility futures. Environmental Research Letters, 2019, 14(9. 095006

[74] Oliveira. (2016). Urban Morphology. The Urban Book Series. Springer.

[75] OpenStreetMap. (2024). OpenStreetMap. http://www.openstreetmap.org/

[76] Panerai, P., Castex, J., Depaule, J.-C., & Samuels, I. (2004). Urban Forms: The Death and Life of the Urban Block. Routledge.

[77] Peng, D., Gui, Z., & Wu, H. (2024). Interpreting the Curse of Dimensionality from Distance Concentration and Manifold Effect (arXiv:2401.00422). arXiv. https://doi.org/10.48550/arXiv.2401.00422

[78] Porta, S., & Romice, O. (2010). Plot-Based Urbanism: Towards Time-Consciousness in Place-Making. University of Strathclyde - Urban Design Studies Unit.

[79] Rey, S. J., & Anselin, L. (2010). PySAL: A Python Library of Spatial Analytical Methods. In M. M. Fischer & A. Getis (Eds.), Handbook of Applied Spatial Analysis: Software Tools, Methods and Applications (pp. 175–193). Springer. https://doi.org/10.1007/978-3-642-03647-7_11

[80] Rong Y, Leemann T, Nguyen T-T, Fiedler L, Qian P, Unhelkar V, Seidel T, Kasneci G, Kasneci E. Towards human-centered explainable AI: A survey of user studies for model explanations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(4): 2104-2122.

[81] Rossi AThe architecture of the city, 1982MIT Press

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

[83] Schirmer, P. M., & Axhausen, K. W. (2019). A Multiscale Clustering of the Urban Morphology for Use in Quantitative Models. In L. D’Acci (Ed.), The Mathematics of Urban Morphology (pp. 355–382). Springer International Publishing. https://doi.org/10.1007/978-3-030-12381-9_16

[84] Schwarz N. Urban form revisited—Selecting indicators for characterising European cities. Landscape and Urban Planning, 2010, 96(1): 29-47.

[85] Scikit-learn. (2024, August 15). scikit-learn: Machine learning in Python. https://scikit-learn.org/stable/index.html

[86] Shach-Pinsly D, Capeluto IG. From form-based to performance-based codes. Sustainability, 2020, 12(14. Article 14

[87] Sitte, C. (1889). City Planning According to Artistic Principles. Dover Publications.

[88] Tishby, N., Pereira, F. C., & Bialek, W. (2000). The information bottleneck method (arXiv:physics/0004057). arXiv. https://doi.org/10.48550/arXiv.physics/0004057

[89] To Vima. (2024, April 24). Council of State Rejects Motion Against Thessaloniki Motorway Project. Tovima.Com. https://www.tovima.com/society/council-of-state-rejects-motion-against-thessaloniki-motorway-project/

[90] Van Nes A, Yamu C. Introduction to Space Syntax in Urban Studies. Springer International Publishing, 2021.

[91] Varoudis, T. (2025). depthmapX [C++]. https://github.com/varoudis/depthmapX (Original work published 2012)

[92] Waggoner, P. D. (2021). Modern Dimension Reduction (arXiv:2103.06885). arXiv. https://doi.org/10.48550/arXiv.2103.06885

[93] Wagner F, Milojevic-Dupont N, Franken L, Zekar A, Thies B, Koch N, Creutzig F. Using explainable machine learning to understand how urban form shapes sustainable mobility. Transportation Research Part d: Transport and Environment, 2022, 111. 103442

[94] Wang J, Biljecki F. Unsupervised machine learning in urban studies: A systematic review of applications. Cities, 2022, 129. 103925

[95] Wang J, Fleischmann M, Venerandi A, Romice O, Kuffer M, Porta S. EO + morphometrics: Understanding cities through urban morphology at large scale. Landscape and Urban Planning, 2023, 233. 104691

[96] Wu C, Wang J, Wang M, Kraak M-J. Machine learning-based characterisation of urban morphology with the street pattern. Computers, Environment and Urban Systems, 2024, 109. 102078

[97] Yang Y, Sun H, Zhang Y, Zhang T, Gong J, Wei Y, Duan Y-G, Shu M, Yang Y, Wu D, Yu D. Dimensionality reduction by UMAP reinforces sample heterogeneity analysis in bulk transcriptomic data. Cell Reports, 2021.

[98] Yerolympos A. Thessaloniki (Salonika) before and after 1917. Twentieth century planning versus 20 centuries of urban evolution. Planning Perspectives, 1988, 3(2): 141-166.

[99] Zakšek K, Oštir K, Kokalj Ž. Sky-view factor as a relief visualization technique. Remote Sensing, 2011, 3(2. Article 2

[100] Zhang T, Ramakrishnan R, Livny M. BIRCH: An efficient data clustering method for very large databases. SIGMOD Record, 1996, 25(2): 103-114.

RIGHTS & PERMISSIONS

The Author(s)