Scholarlink

<p>Climate change is a critical global challenge that significantly impacts physical factors and ecological systems. Rapid urbanization has accelerated changes in land use/land cover (LULC), affecting land surface temperature (LST), diminishing vegetation cover as shown by decreased Normalized Difference Vegetation Index (NDVI) values and worsening urban heat island (UHI) effects. This study employs remote sensing, GIS-based spatial analysis, and machine learning algorithms to assess the spatiotemporal changes in LULC, NDVI, and LST in the Guwahati Metropolitan Area from 2000 to 2024, with a predictive outlook for 2029. The results indicate a 9.36% increase in built-up areas, coinciding with a 5.73% decline in agricultural land and a 3.56% reduction in vegetation cover. The inverse correlation between NDVI and LST highlights the significant role of vegetation in mitigating urban heat, with maximum NDVI values decreasing from 0.86 in 2020 to 0.81 in (Chakroborty <CitationRef CitationID="CR10">2024</CitationRef>), while maximum LST increased from 44.70&#xa0;°C to 47.38&#xa0;°C over the study period. The UHI intensity has intensified, with urban cores experiencing a temperature rise of 3.33&#xa0;°C in 2015 to 4.14&#xa0;°C in 2024, exacerbating thermal stress in densely populated areas. The study also captures the temporary impact of the COVID-19 lockdown in 2020, where reduced human activities led to an increase in NDVI values and a decline in LST. The projected LULC for 2029 suggests further urban expansion, with built-up areas reaching 40–45%, likely leading to additional thermal stress. The integration of machine learning-based predictive modeling provides a robust framework for future urban planning and environmental sustainability initiatives. This study provides important insights into urban ecological transformations driven by climate change and human activities.</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

Advanced geospatial synthesis of urban heat Island dynamics: interlinking climate change, land use/land cover, vegetative indices, and thermal variability in Guwahati metropolitan area, assam, India

  • 期刊论文

  • 发表日期：

    2025年8月26日

查看全文
  • Toushif Jaman,
  • Suraj Kumar Swain,
  • Jenita Mary Nongkynrih,
  • Kasturi Chakraborty,
  • Rekha Bharali Gogoi,
  • K. K. Sarma,
  • S. P. Aggarwal

摘要

Climate change is a critical global challenge that significantly impacts physical factors and ecological systems. Rapid urbanization has accelerated changes in land use/land cover (LULC), affecting land surface temperature (LST), diminishing vegetation cover as shown by decreased Normalized Difference Vegetation Index (NDVI) values and worsening urban heat island (UHI) effects. This study employs remote sensing, GIS-based spatial analysis, and machine learning algorithms to assess the spatiotemporal changes in LULC, NDVI, and LST in the Guwahati Metropolitan Area from 2000 to 2024, with a predictive outlook for 2029. The results indicate a 9.36% increase in built-up areas, coinciding with a 5.73% decline in agricultural land and a 3.56% reduction in vegetation cover. The inverse correlation between NDVI and LST highlights the significant role of vegetation in mitigating urban heat, with maximum NDVI values decreasing from 0.86 in 2020 to 0.81 in (Chakroborty 2024), while maximum LST increased from 44.70 °C to 47.38 °C over the study period. The UHI intensity has intensified, with urban cores experiencing a temperature rise of 3.33 °C in 2015 to 4.14 °C in 2024, exacerbating thermal stress in densely populated areas. The study also captures the temporary impact of the COVID-19 lockdown in 2020, where reduced human activities led to an increase in NDVI values and a decline in LST. The projected LULC for 2029 suggests further urban expansion, with built-up areas reaching 40–45%, likely leading to additional thermal stress. The integration of machine learning-based predictive modeling provides a robust framework for future urban planning and environmental sustainability initiatives. This study provides important insights into urban ecological transformations driven by climate change and human activities.