Scholarlink

<p>Rapid urban expansion in emerging metropolitan regions has created significant challenges for sustainable land management, environmental conservation, and infrastructure planning. Gurugram District, one of India’s fastest-growing urban centers within the National Capital Region (NCR), has experienced substantial land-use transformation over the last decade; however, a comprehensive geospatial assessment of its spatial growth dynamics and future expansion patterns remains limited. Therefore, the present study aims to quantify the spatiotemporal patterns of urban expansion, evaluate the intensity and direction of urban sprawl, and predict future urban growth using integrated geospatial and machine-learning approaches. Multi-temporal Sentinel-2 imagery (2015–2025), Enhanced Vegetation Index (EVI)-based built-up extraction, supervised classification, Shannon’s entropy analysis, factor analysis, multiple regression, ANN–Markov Chain modelling, and XGBoost algorithms were employed to assess urban growth dynamics in Gurugram District. The results indicate that built-up area increased substantially from 102.50&#xa0;km² in 2015 to 168.20&#xa0;km² in 2025, primarily driven by infrastructure-led development along the Dwarka Expressway, Southern Peripheral Road, and New Gurugram corridors. Shannon’s entropy analysis revealed increasing spatial dispersion, indicating a transition from relatively compact urban development toward fragmented peri-urban sprawl. Factor analysis and regression modelling identified economic forces, accessibility, administrative processes, and opportunity-driven variables as the major determinants of urban expansion, while environmental variables exhibited comparatively lower influence. Future urban growth simulations demonstrated high predictive performance (AUC &gt; 0.90) and projected intensified expansion toward transport-oriented peri-urban sectors by 2030. The findings highlight the growing pressure on agricultural land, ecological systems, and urban infrastructure, emphasizing the need for integrated spatial planning, sustainable land-use management, and evidence-based urban policy interventions for Gurugram’s future 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

Quantifying urban expansion in Gurugram: a multi-sensor GIS, entropy, and machine-learning approach

  • 期刊论文

  • 发表日期：

    2026年7月25日

查看全文
  • Agradeep Mohanta,
  • Ameet Yadav,
  • Naveen Yadav,
  • Kalyan Malik,
  • Sanjay Kumar,
  • Aman Kumar,
  • Pardeep Kumar,
  • Sultan Singh

摘要

Rapid urban expansion in emerging metropolitan regions has created significant challenges for sustainable land management, environmental conservation, and infrastructure planning. Gurugram District, one of India’s fastest-growing urban centers within the National Capital Region (NCR), has experienced substantial land-use transformation over the last decade; however, a comprehensive geospatial assessment of its spatial growth dynamics and future expansion patterns remains limited. Therefore, the present study aims to quantify the spatiotemporal patterns of urban expansion, evaluate the intensity and direction of urban sprawl, and predict future urban growth using integrated geospatial and machine-learning approaches. Multi-temporal Sentinel-2 imagery (2015–2025), Enhanced Vegetation Index (EVI)-based built-up extraction, supervised classification, Shannon’s entropy analysis, factor analysis, multiple regression, ANN–Markov Chain modelling, and XGBoost algorithms were employed to assess urban growth dynamics in Gurugram District. The results indicate that built-up area increased substantially from 102.50 km² in 2015 to 168.20 km² in 2025, primarily driven by infrastructure-led development along the Dwarka Expressway, Southern Peripheral Road, and New Gurugram corridors. Shannon’s entropy analysis revealed increasing spatial dispersion, indicating a transition from relatively compact urban development toward fragmented peri-urban sprawl. Factor analysis and regression modelling identified economic forces, accessibility, administrative processes, and opportunity-driven variables as the major determinants of urban expansion, while environmental variables exhibited comparatively lower influence. Future urban growth simulations demonstrated high predictive performance (AUC > 0.90) and projected intensified expansion toward transport-oriented peri-urban sectors by 2030. The findings highlight the growing pressure on agricultural land, ecological systems, and urban infrastructure, emphasizing the need for integrated spatial planning, sustainable land-use management, and evidence-based urban policy interventions for Gurugram’s future development.