AI Urban Voids: A Data-Driven Approach to Urban Activation

Citations of this article
Mendeley users who have this article in their library.

This article is free to access.


With the development of digital technologies, big urban data is now readily available online. This opens the opportunity to utilize new data and create new relationships within multiple urban features for cities. Moreover, new computational design techniques open a new portal for architects and designers to reinterpret this urban data and provide much better-informed design decisions. The “AI Urban Voids'' project is defined as a data-driven approach to analyze and predict the strategic location for urban uses in the addition of amenities within the city. The location of these urban amenities is evaluated based on predictions and scores followed by a series of urban analyses and simulations using K-Means clustering. Furthermore, these results are then visualized in a web-based platform; likewise, the aim is to create a tool that will work on a feedback loop system that constantly updates the information. This paper explains the use of different datasets from Five cities including Melbourne, Sydney, Berlin, Warsaw, and Sao Paulo. Python, Osmx libraries and K-means clustering open the way to manipulate large data sets by introducing a collection of computational processes that can override traditional urban analysis.




Algamdey, A., Mastalski, A., Chronis, A., Gurung, A., Vargas, F. R., Bodenbender, G., & Khairallah, L. (2023). AI Urban Voids: A Data-Driven Approach to Urban Activation. In Computational Design and Robotic Fabrication (Vol. Part F1309, pp. 293–303). Springer.

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free