Scholarlink

<p>Rapid urbanization transforms urban metabolism and intensifies the Surface Urban Heat Island (SUHI) effect. However, the link between metabolic processes and urban thermal dynamics remains poorly understood. This study presents a remote sensing and machine learning framework to explore how changes in urban metabolism influenced thermal patterns in Guangdong, China, from 2001 to 2021. The findings show that urban metabolic activity increased by 15.87%, contributing to a net SUHI intensification of + 1.3&#xa0;° C over the two decades. A significant relationship (<i>P</i> &lt; 0.01) was observed between metabolic indicators and surface temperature, underscoring the importance of land surface characteristics in thermal regulation . The Support vector regression model projected SUHI intensities to increase by 0.44&#xa0;° C in 2025 and by 0.54&#xa0;° C in 2029. These trends highlight the urgent need for strategic green infrastructure interventions. This study introduces a metabolism-informed predictive framework that integrates spectral indices, thermal indicators, and machine learning to model future urban heat dynamics. The results offer practical insights for urban planners and policymakers working toward climate-resilient and sustainable city development.</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

Metabolic Transformation and Urban Heat Island Dynamics: Achieving Thermal Balance in Chinese Megacities

  • 期刊论文

  • 发表日期：

    2026年1月9日

查看全文
  • Abubakar Sabo Ahmad,
  • Li Yi,
  • Asim Biswas,
  • Xiaoyan Song,
  • Javlonbek Ishchanov,
  • Hamsa Mohamded Kadambot Siddique

摘要

Rapid urbanization transforms urban metabolism and intensifies the Surface Urban Heat Island (SUHI) effect. However, the link between metabolic processes and urban thermal dynamics remains poorly understood. This study presents a remote sensing and machine learning framework to explore how changes in urban metabolism influenced thermal patterns in Guangdong, China, from 2001 to 2021. The findings show that urban metabolic activity increased by 15.87%, contributing to a net SUHI intensification of + 1.3 ° C over the two decades. A significant relationship (P < 0.01) was observed between metabolic indicators and surface temperature, underscoring the importance of land surface characteristics in thermal regulation . The Support vector regression model projected SUHI intensities to increase by 0.44 ° C in 2025 and by 0.54 ° C in 2029. These trends highlight the urgent need for strategic green infrastructure interventions. This study introduces a metabolism-informed predictive framework that integrates spectral indices, thermal indicators, and machine learning to model future urban heat dynamics. The results offer practical insights for urban planners and policymakers working toward climate-resilient and sustainable city development.