What Is My Plaza for? - Implementing a Machine Learning Strategy for Public Events Prediction in the Urban Square

Aug 5, 2026

Upload by Liam

Plazas underpin public life, historically serving as fora for trade, interaction, and debate, yet modern urbanism often reduced their social value. This work re-activates plazas for inclusion and resilience by linking event suitability to measurable geometric and urban features. It applies machine learning to classify event types using urban indicators across external, geometric-shape, and design factors. Model capability is limited by a small set of 15 Madrid plazas augmented to 2025 scenarios via self-organising maps, with local evaluation in Grasshopper and transfer to other plazas by geographic proximity.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

Introduction

Research question and objectives

Motivation and literature gap

State of the Art

From event detection to event prediction

Urban Planning 2025 • Volume 10 • Article 8551 [https://doi.org/10.17645/up.8551](https://doi.org/10.17645/up.8551) ARTICLE Open Access Journal What Is My Plaza for? Implementing a Machine Learning Strategy for Public Events Prediction in the Urban Square Jumana Hamdani 1,2 , Pablo Antuña Molina 3 , Lucía Leva Fuentes 3 , Hesham Shawqy 3 , Gabriella Rossi 4 , and David Andrés León 3 1 School of Information Systems and Technology Management, University of New South Wales, Australia 2 Department of Spatial Planning, Blekinge Institute of Technology, Sweden 3 IAAC—Institute for Advanced Architecture of Catalonia, Spain 4 CITA, Royal Danish Academy, Denmark Correspondence: Jumana Hamdani ([j.hamdani@unsw.edu.au](j.hamdani@unsw.edu.au)) Submitted: 29 April 2024 Accepted: 22 July 2024 Published: 21 January 2025 Issue: This article is part of the issue “AI for and in Urban Planning” edited by Tong Wang (TU Delft) and Neil Yorke‐Smith (TU Delft), fully open access at [https://doi.org/10.17645/up.i388](https://doi.org/10.17645/up.i388) Abstract Plazas are an essential pillar of public life in our cities. Historically, they have been seen as public fora, hosting public events that fostered trade, interaction, and debate. However, with the rise of modern urbanism, city planners considered them as part of a larger strategic development scheme overlooking their social importance. As a result, plazas have lost their function and value. In recent years, awareness has risen of the need to re‐activate these public spaces to strive for social inclusion and urban resilience. Geometric and urban features of plazas and their surroundings often suggest what kinds of usage the public can make of them. In this project, we explore the application of machine learning to predict the suitability of events in public spaces, aiming to enhance urban plaza design. Learning from traditional urbanism indicators, we consider factors associated with the features of the public space, such as the number of people and the high degree of comfort, which are evolved from three subcategories: external factors, geometric shape, and design factors. We acknowledge that the predictive capability of our model is constrained by a relatively small dataset, comprising 15 real plazas in Madrid augmented digitally to 2025 fictional scenarios through self‐organising maps. The article details the methods to quantify and enumerate quantitative urban features. With a categorical target variable, a classification model is trained to predict the type of event in the urban space. The model is then evaluated locally in Grasshopper by visualising a parametric verified geometry and deploying the model on other existing plazas worldwide regarding geographical proximity to Madrid, where to share or not the same cultural and environmental conditions. Despite these limitations, our findings offer valuable insights into the potential of machine learning in urban planning, suggesting pathways for future research to expand upon this foundational study. © 2025 by the author(s), licensed under a Creative Commons Attribution 4 .0 International License (CC BY) . 1 | Keywords
data classification; event prediction; machine learning; Madrid; plaza; public squares; self‐organising maps; urban planning | | --- | | 1. Introduction
The need for event prediction models in an urban environment is essential for all kinds of applications, from natural disaster preparation to urban management, planning, and development of smart cities (Mukhina et al., 2019) . This rapid change in the relationship between events and public space highlights the features of the eventful city (Richards & Colombo, 2017) and how their form defines them, duration, content, and effects, determined to a certain extent by urban space and process (Richards & Palmer, 2010) . The emphasis on people’s behaviour in the public space and how it is affected by the built environment (Lynch, 1964) and i

FAQs

How does the study predict which events are suitable for urban plazas?

It trains a classification model with a categorical target variable to predict the type of public event based on quantifiable urban features of plazas and their surroundings.

What factors and feature categories does the model use?

The features are derived from three subcategories: external factors, geometric shape, and design factors, aimed at capturing indicators connected to public usage.

What limitation affects predictive performance in this article?

Predictive capability is constrained by a relatively small dataset of 15 real plazas in Madrid, digitally augmented to 2025 fictional scenarios using self-organising maps.

Aug 5, 2026

Upload by Liam