Learning to cluster urban areas: two competitive approaches and an empirical validation

Camila Vera; Francesca Lucchini; Naim Bro; Marcelo Mendoza; Hans Löbel; Felipe Gutiérrez; Jan Dimter; Gabriel Cuchacovic; Axel Reyes; Hernán Valdivieso; Nicolás Alvarado; Sergio Toro

doi:10.1140/epjds/s13688-022-00374-2

2022 Impact factor 3.6

Open Access

EPJ Data Sci. (2022) 11: 62
https://doi.org/10.1140/epjds/s13688-022-00374-2

Regular Article

Learning to cluster urban areas: two competitive approaches and an empirical validation

Camila Vera¹^,2^,3, Francesca Lucchini¹^,3, Naim Bro²^,4, Marcelo Mendoza¹^,2^,3^d, Hans Löbel¹^,2^,3^,5, Felipe Gutiérrez¹^,3, Jan Dimter¹^,2, Gabriel Cuchacovic¹, Axel Reyes¹^,6, Hernán Valdivieso¹^,2, Nicolás Alvarado¹^,3 and Sergio Toro²^,7^,8

¹ Department of Computer Science, Pontificia Universidad Católica de Chile, Santiago, Chile
² Millennium Institute for Foundational Research on Data (IMFD), Santiago, Chile
³ National Center of Artificial Intelligence, Santiago, Chile
⁴ Faculty of Government, Universidad Adolfo Ibáñez, Santiago, Chile
⁵ Department of Transport Engineering and Logistics, Pontificia Universidad Católica de Chile, Santiago, Chile
⁶ Department of Informatics, Universidad Técnica Federico Santa María, Santiago, Chile
⁷ Public Administration and Political Science, Universidad de Concepción, Concepción, Chile
⁸ School of Government, Universidad Mayor, Santiago, Chile

^d marcelo.mendoza@uc.cl

Received: 12 July 2022
Accepted: 5 December 2022
Published online: 20 December 2022

Abstract

Urban clustering detects geographical units that are internally homogeneous and distinct from their surroundings. It has applications in urban planning, but few studies compare the effectiveness of different methods. We study two techniques that represent two families of urban clustering algorithms: Gaussian Mixture Models (GMMs), which operate on spatially distributed data, and Deep Modularity Networks (DMONs), which work on attributed graphs of proximal nodes. To explore the strengths and limitations of these techniques, we studied their parametric sensitivity under different conditions, considering the spatial resolution, granularity of representation, and the number of descriptive attributes, among other relevant factors. To validate the methods, we asked residents of Santiago, Chile, to respond to a survey comparing city clustering solutions produced using the different methods. Our study shows that DMON is slightly preferred over GMM and that social features seem to be the most important ones to cluster urban areas.

Key words: Urban clustering / Graph Neural Networks / Gaussian Mixture Models

© The Author(s) 2022

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, 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 changes were made. 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/4.0/.