Speaker
Description
Urban planning is inherently linked to the design and production of spaces, yet traditional methods often struggle to address the complexity of contemporary urban challenges. Understanding the relationship between urban form and historical development is crucial for designing sustainable and resilient cities. This study explores the potential of emerging computational methods to enhance urban morphological analysis, offering a scalable and systematic approach to identifying and classifying urban patterns.
Urban settlements evolve as mosaics of spatial patterns, shaped by historical processes and urban dynamics. Recognizing these patterns through a morphological perspective is essential for both historical analysis and forward-looking planning. Classic urban morphology, namely the historic-geographical approach, laid the foundation for the concept of Morphological Regions, which is based on the typomorphological classification of unitary areas, delimited by their degree of internal morphological similarity. However, from a methodological point of view, the delimitation of these regions remains labour-intensive, hindering the definition of these morphologically homogeneous regions in a scalable and systematic way.
The richness and robustness of the concept allow us to transfer some of the Conzenian premises of Morphological Regions into a coherent framework for a quantitative morphological analysis. By integrating geospatial technologies, quantitative metrics, and machine learning techniques, this study advances a scalable framework for spatial pattern analysis.
The proposed method operates on two levels. First, it introduces an algorithmic classification system based on the hierarchical structure of urban form components—streets, blocks, plots, and buildings—using statistical clustering techniques. Second, it integrates these classified components into a spatial model that delineates urban patterns based on their frequency and distribution. The research design includes the development of a standardized representation of urban form elements, selection of key morphological measures informed by literature, and the application of computational techniques within a GIS-based analytical platform.
Empirical studies conducted in São Paulo, Brazil, demonstrate how this framework can systematically classify and describe urban form patterns, supporting both historical analysis and contemporary planning strategies. The ability to quantitatively assess and visualize urban morphology offers planners a data-driven tool for evidence-based decision-making, bridging the gap between traditional urban analysis and emerging technologies. Moreover, by integrating spatial data analytics into urban morphological studies, this approach contributes to the broader discourse on computational urbanism and digital tools for transformative planning.
By aligning urban morphology with cutting-edge geospatial analysis, this research advances the role of emerging technologies in spatial planning, offering new insights into how digital innovations can enhance our understanding of urban systems and inform more resilient and adaptive urban development strategies.
References
Berghauser Pont, M., Stavroulaki, G., Bobkova, E., Gil, J., Marcus, L., Olsson, J., Sun, K., Serra, M., Hausleitner, B., Dhanani, A., Legeby, A., 2019. The spatial distribution and frequency of street, plot and building types across five European cities. Environ. Plan. B Urban Anal. City Sci. 46, 1226–1242.
Conzen, M.R.G., 1960. Alnwick, Northumberland: A Study in Town-Plan Analysis, Institute of British Geographers. George Philip & Son, London.
Oliveira, V., 2016. Urban Morphology: An Introduction to the Study of the Physical Form of Cities, The Urban Book Series. Springer International Publishing, Cham.
Serra, M., Gil, J., Pinho, P., 2017. Towards an understanding of morphogenesis in metropolitan street-networks. Environ. Plan. B Urban Anal. City Sci. 44, 272–293.
| Keywords | typomorphologies; hierarchy; machine learning; GIS |
|---|---|
| Best Congress Paper Award | No |
