Scholarlink

<p>Constructing a predictive model for urban heat islands (UHIs) is essential for accurately assessing urban thermal environments and guiding sustainable development strategies. Previous studies typically modeled urban heat island based on the entire city, ignoring the differences of influencing factors between local areas. Therefore, this article firstly explores the impact of influencing factors on local heat island based on Local Climate Zones (LCZ) zoning using SHAP (SHapley Additive ExPlanations) analysis, and then designed up to 21 features for constructing prediction models using machine learning technology in each LCZ region. Experimental results indicate that the Random Forest model offers higher accuracy in predicting UHI, with accuracy exceeding 75%. The SHAP analysis found significant differences in the features that affect urban heat island prediction in different regions. Totally, impervious surface density (ISD), building density (BD), green space density (GSD), and the richness of vegetation are most important features in model building. This study not only improves the accuracy of UHI predictions, but also provides the groundwork for future research into the dynamic planning of urban heat islands.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Influencing factors and predictive modeling of the urban heat Island in Guangzhou, China

  • 期刊论文

  • 发表日期：

    2025年7月9日

查看全文
  • Yiming Huang,
  • Ping Du,
  • Hui Li,
  • Jinqu Zhang

摘要

Constructing a predictive model for urban heat islands (UHIs) is essential for accurately assessing urban thermal environments and guiding sustainable development strategies. Previous studies typically modeled urban heat island based on the entire city, ignoring the differences of influencing factors between local areas. Therefore, this article firstly explores the impact of influencing factors on local heat island based on Local Climate Zones (LCZ) zoning using SHAP (SHapley Additive ExPlanations) analysis, and then designed up to 21 features for constructing prediction models using machine learning technology in each LCZ region. Experimental results indicate that the Random Forest model offers higher accuracy in predicting UHI, with accuracy exceeding 75%. The SHAP analysis found significant differences in the features that affect urban heat island prediction in different regions. Totally, impervious surface density (ISD), building density (BD), green space density (GSD), and the richness of vegetation are most important features in model building. This study not only improves the accuracy of UHI predictions, but also provides the groundwork for future research into the dynamic planning of urban heat islands.