Scholarlink

<p>Metro route site selection plays a crucial role in urban mobility planning, requiring an integrated approach that considers multiple geospatial and socio-environmental factors. This study develops a smart optimization framework for metro route alignment in Nagercoil City, Tamil Nadu, India, utilizing machine learning, remote sensing, GIS, and AHP techniques. The study predicted LULC for 2045 using ANNs and Logistic Regression, integrating traffic density, population distribution, and proximity to roads, railways, water bodies, intersections, key locations, geomorphology, soil type, lithology, NDVI, LST, elevation, slope, aspect, and hill shade. AHP-based weighted overlay analysis classified metro route suitability into five categories: Very High (18.58%), High (18.70%), Moderate (20.33%), Low (20.30%), and Very Low (22.10%). Three metro route plans were proposed. Metro Plan A (Red Line) from Chunkankadai to Kanniyakumari Beach spans 23.42&#xa0;km with 22 stations, covering Very High and High suitability zones (96.85% accuracy). Metro Plan B (Purple Line) from Vadasery to Manakudy Beach extends 13.75&#xa0;km with 20 stations, passing through Very High, High, and Moderate zones (89.26% accuracy). Metro Plan C (Blue Line) from Muttom Beach to Azhagappapuram covers 35.65&#xa0;km with 37 stations, also spanning Very High, High, and Moderate zones (82.65% accuracy). Comparative analysis based on station count, inter-station metrics, route length, and accuracy identified Metro Plan A (Red Line) as the most suitable alignment for future urban development. This study demonstrates the effectiveness of machine learning and geospatial techniques for metro route optimization in Nagercoil City, enabling data-driven planning to enhance connectivity, reduce congestion, and improve accessibility.</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

Optimizing future metro route alignment with machine learning and geospatial techniques: a case study of Nagercoil city, Tamil Nadu

  • 期刊论文

  • 发表日期：

    2025年7月28日

查看全文
  • Ahamed Ibrahim Abdul Rahim,
  • Muthusankar Gowrappan,
  • Prabhakaran Moorthy,
  • Vignesh Chelladurai,
  • Rahamathulla Amjath,
  • Bharathi Balu,
  • Kiruthika Srinivasan,
  • Tune Usha,
  • Lakshumanan Chokkalingam

摘要

Metro route site selection plays a crucial role in urban mobility planning, requiring an integrated approach that considers multiple geospatial and socio-environmental factors. This study develops a smart optimization framework for metro route alignment in Nagercoil City, Tamil Nadu, India, utilizing machine learning, remote sensing, GIS, and AHP techniques. The study predicted LULC for 2045 using ANNs and Logistic Regression, integrating traffic density, population distribution, and proximity to roads, railways, water bodies, intersections, key locations, geomorphology, soil type, lithology, NDVI, LST, elevation, slope, aspect, and hill shade. AHP-based weighted overlay analysis classified metro route suitability into five categories: Very High (18.58%), High (18.70%), Moderate (20.33%), Low (20.30%), and Very Low (22.10%). Three metro route plans were proposed. Metro Plan A (Red Line) from Chunkankadai to Kanniyakumari Beach spans 23.42 km with 22 stations, covering Very High and High suitability zones (96.85% accuracy). Metro Plan B (Purple Line) from Vadasery to Manakudy Beach extends 13.75 km with 20 stations, passing through Very High, High, and Moderate zones (89.26% accuracy). Metro Plan C (Blue Line) from Muttom Beach to Azhagappapuram covers 35.65 km with 37 stations, also spanning Very High, High, and Moderate zones (82.65% accuracy). Comparative analysis based on station count, inter-station metrics, route length, and accuracy identified Metro Plan A (Red Line) as the most suitable alignment for future urban development. This study demonstrates the effectiveness of machine learning and geospatial techniques for metro route optimization in Nagercoil City, enabling data-driven planning to enhance connectivity, reduce congestion, and improve accessibility.