Scholarlink

<p>The study aimed to assess land use/land cover (LULC) changes in the highly dynamic region of mining area adjacent to Dhanbad city in the eastern India and its adjoining rural areas, with a particular focus on the proximity to open-cast mining zones using hybrid Convolution Neural Network (CNN) model using Landsat-5 Thematic Mapper and Landsat-8 Operational Land Imager for the 25 years from 2000 to 2025. The study categorised the land into seven classes: Waterbody, Built-up, Barren, Mining, Grassland, Wetland, and Dense-Vegetation. The CNN model uses hybrid 1 × 1 and 3 × 3 spatial data to train and classify LULC of the region for the years 2000, 2005, 2010, 2015, 2020, and 2025 with accuracy 94.0%, 93.8%, 93.9%, 95.6%, 93.8%, and 93.0%, respectively. The findings revealed a significant increase in built-up areas, mining, and dense vegetation by 158%, 76%, and 88%, while a decrease in barren, grassland and wetland classes by 88.82%, 31.89% and 47.43% respectively, from 2000 to 2025. The urban region, being more dynamic, experienced a substantial area change in built-up, mining, grassland, and dense-vegetation classes, indicating greater dynamism compared to the rural region. The extensive afforestation practices for land reclamation in mining and barren areas reveal a significant increase in the dense vegetation in urban and rural regions. The study provides valuable insights which can contribute to effective urban and rural planning strategies by highlighting the significant changes and trends in land use associated with mining activities and their impacts on surrounding regions, such as coal fire propagation, mine reclamation and relocation and rehabilitation.</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

Evaluating the Dynamics of Urban and Rural Areas Adjacent to the Coal Mining Region of Eastern India Using Landsat time Series Data

  • 期刊论文

  • 发表日期：

    2026年2月2日

查看全文
  • Wilson Kandulna,
  • Manish Kumar Jain

摘要

The study aimed to assess land use/land cover (LULC) changes in the highly dynamic region of mining area adjacent to Dhanbad city in the eastern India and its adjoining rural areas, with a particular focus on the proximity to open-cast mining zones using hybrid Convolution Neural Network (CNN) model using Landsat-5 Thematic Mapper and Landsat-8 Operational Land Imager for the 25 years from 2000 to 2025. The study categorised the land into seven classes: Waterbody, Built-up, Barren, Mining, Grassland, Wetland, and Dense-Vegetation. The CNN model uses hybrid 1 × 1 and 3 × 3 spatial data to train and classify LULC of the region for the years 2000, 2005, 2010, 2015, 2020, and 2025 with accuracy 94.0%, 93.8%, 93.9%, 95.6%, 93.8%, and 93.0%, respectively. The findings revealed a significant increase in built-up areas, mining, and dense vegetation by 158%, 76%, and 88%, while a decrease in barren, grassland and wetland classes by 88.82%, 31.89% and 47.43% respectively, from 2000 to 2025. The urban region, being more dynamic, experienced a substantial area change in built-up, mining, grassland, and dense-vegetation classes, indicating greater dynamism compared to the rural region. The extensive afforestation practices for land reclamation in mining and barren areas reveal a significant increase in the dense vegetation in urban and rural regions. The study provides valuable insights which can contribute to effective urban and rural planning strategies by highlighting the significant changes and trends in land use associated with mining activities and their impacts on surrounding regions, such as coal fire propagation, mine reclamation and relocation and rehabilitation.