Skip to main navigation Skip to search Skip to main content

Predicting urban vitality and pedestrian road safety in urban areas based on machine learning

  • Weijie Qiao
  • , Hao Zheng*
  • *Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

9 Downloads (CityUHK Scholars)

Abstract

Urban vitality and pedestrian road safety are two critical indicators of the quality of urban life, both of which are heavily influenced by spatial factors in the urban environment. However, traditional quantitative models rarely address the relationship between these issues simultaneously and often lack the capability to provide real-time, interactive feedback for urban planners. This research aims to utilize Generative Adversarial Networks (GANs) to develop a predictive model of generating city maps and heatmaps that represent urban vitality and pedestrian road safety. Using San Francisco as a case study, we integrate pedestrian crash data, census population data, and other built environment data to train the predictive model with a dataset containing over a thousand pairs of images. After model training, the best-performing models are selected in the experiments of various urban scenarios simulation, assessing the prediction accuracy of urban vitality and pedestrian road safety. The results indicate that this approach has a high prediction accuracy of urban vitality and pedestrian road safety, especially allowing for effective evaluation of the changes in the impact of pre- and post-design modification for practical applications. Additionally, the research introduces a novel methodology that offers a framework for future studies, showing its potential to be generalized and predict the issues in complex urban contexts.

© 2025 The Author(s). Published by Elsevier Ltd.
Original languageEnglish
Article number106193
Number of pages23
JournalCities
Volume166
Online published3 Jul 2025
DOIs
Publication statusPublished - Nov 2025

Funding

This research was funded by the New Faculty Start-up Grant (Project No. 9610653) from the City University of Hong Kong and also supported by the China Scholarship Council (No. 202308250007).

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

  1. SDG 3 - Good Health and Well-being
    SDG 3 Good Health and Well-being
  2. SDG 11 - Sustainable Cities and Communities
    SDG 11 Sustainable Cities and Communities

Research Keywords

  • Urban vitality
  • Pedestrian road safety
  • Urban design
  • Generative adversarial networks

Publisher's Copyright Statement

  • This full text is made available under CC-BY-NC-ND 4.0. https://creativecommons.org/licenses/by-nc-nd/4.0/

Fingerprint

Dive into the research topics of 'Predicting urban vitality and pedestrian road safety in urban areas based on machine learning'. Together they form a unique fingerprint.

Cite this