Bai, Zishen;
Yu, Jiaqi;
Guo, Kening;
(2025)
A Revisit of the Fifteen-minute City Model: Exploring the trade-off between urban accessibility and thermal environment using interpretable machine learning.
In:
Proceedings of the 43rd Education and Research in Computer Aided Architectural Design in Europe (eCAADe) Conference.
(pp. pp. 237-246).
Middle East Technical University, Faculty of Architecture, Department of Architecture
Preview |
Text
ecaade2025_318.pdf - Published Version Download (425kB) | Preview |
Abstract
Global warming continues to threaten urban residents, and trends have intensified in recent years. The Fifteen Minute City (FMC) framework has been recognised as an important solution to the urban environmental challenge and has met the needs of residents. However, recent studies have found that FMC can negatively impact the thermal environment in cities and may disrupt constructed systems. The value of FMC has been widely debated in recent years, and consensus has not been reached due to the influence of binary assessments in the past. Therefore, to further explore the relationship between FMC and the urban thermal environment, this study introduces an interpretable machine learning approach to quantitatively investigate the relationship between FMC scores and Land Surface Temperature (LST) in Greater London. The study uses the XGBoost model and the SHAP tool to build analyses for LST and accessibility indicators based on a 500 m grid (n = 5567). The training results explained 76% of the LST phenomena. The results show that overall accessibility and distance to services are nonlinearly related to LST. High accessibility may lead to a higher industrial density and a more compact urban layout, thus worsening the thermal environment. In the FMC framework, a reasonable distance (500-1000m) for residents to reach services can achieve a trade-off with the thermal environment. This study revisits the FMC framework from new techniques and perspectives to provide further theoretical support rather than rejecting it. The FMC framework shows strong potential in urban environmental and social service issues and can be further enhanced in the future.
| Type: | Proceedings paper |
|---|---|
| Title: | A Revisit of the Fifteen-minute City Model: Exploring the trade-off between urban accessibility and thermal environment using interpretable machine learning |
| Event: | 43rd Education and Research in Computer Aided Architectural Design in Europe (eCAADe) Conference |
| Location: | Ankara, Turkey |
| Dates: | 3rd-5th September 2025 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://ecaade2025.metu.edu.tr/ |
| Language: | English |
| Additional information: | This version is the version of record. For information on re-use, please refer to the publisher's terms and conditions. |
| Keywords: | 15-Minute City, Accessibility, Urban thermal environment, Interpretable machine learning, Trade-off |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment > Bartlett School Env, Energy and Resources |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10218771 |
Archive Staff Only
 |
View Item |
