94% of researchers rate our articles as excellent or good
Learn more about the work of our research integrity team to safeguard the quality of each article we publish.
Find out more
ORIGINAL RESEARCH article
Front. Public Health
Sec. Environmental Health and Exposome
Volume 13 - 2025 | doi: 10.3389/fpubh.2025.1490857
This article is part of the Research Topic Multi-scale Urban Built Environment and Human Health View all 9 articles
Optimization of Urban Green Space in Wuhan Based on Machine Learning Algorithm from the Perspective of Healthy City
Provisionally accepted- 1 School of Social & Political Sciences, University of Glasgow, Glasgow, Scotland, United Kingdom
- 2 School of Art, Hubei University, Wuhan, China
In order to address the uneven distribution of green space resources, the low green coverage rate, and the associated health issues and urban ecological challenges in Wuhan’s urban areas, this study adopts a perspective of healthy city development. It constructs a multivariable model based on random forest and Support Vector Machine algorithms to assess the impact of key indicators on urban green space. The study integrates core indicators from three dimensions: residents’ health, environmental quality, and community interaction. Multiple linear regression analysis is employed to evaluate the potential benefits of green space optimization on the city’s economic performance and social structure. The results indicate that optimizing health and environmental quality indices has a significant positive impact on green space development. Green space, through improving residents’ health and extending life expectancy, drives a 73% increase in economic efficiency. Meanwhile, by enhancing community cohesion and improving environmental quality, improvements in social structure are achieved at rates of 61% and 52%, respectively. Additionally, the model demonstrates high stability and excellent adaptability after multiple iterations, providing a solid theoretical foundation and quantitative basis for optimizing the green space layout in the study area. The study reveals the multidimensional value of green space optimization in promoting urban health, economic growth, and social stability. It aims to provide scientific decision-making support and practical guidance for green space planning and management in healthy cities.
Keywords: machine learning, Random Forest algorithm, Support Vector Machine algorithm, Optimization of urban green space, Healthy city
Received: 03 Sep 2024; Accepted: 18 Feb 2025.
Copyright: © 2025 Zhou, Zou and Xiong. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Xiaofei Zou, School of Art, Hubei University, Wuhan, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.