Scholarlink

<p>This study presents a comprehensive spatio-temporal analysis and prediction of land use and land cover (LULC) changes in the Amritsar district of Punjab, India, using a Cellular Automata-Artificial Neural Network (CA-ANN) model. Amritsar district has experienced significant land use transformations over the past decades. Satellite images from the years 1990, 2000, 2010, and 2020 were utilized, sourced from the USGS/NASA Landsat Program via Google Earth Engine. The Random Forest classifier was employed for LULC classification, distinguishing between water bodies, agriculture, vegetation, built-up areas, and bare land. Future LULC changes were simulated using the CA-ANN model implemented in QGIS through the MOLUSCE tool. The study observed substantial urban growth at the expense of agricultural and vegetative land, predicting continued urban expansion up to 2050. The findings highlight a 59.0% increase in built-up areas and significant decreases in vegetation (88.1%) and water bodies (47.1%) by 2050. These trends underscore the need for strategic urban planning and sustainable land use practices to mitigate adverse environmental impacts. This research provides critical insights for policymakers and urban planners to ensure balanced development, maintaining ecological integrity alongside economic growth in the Amritsar district.</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

Modeling spatio-temporal land use dynamics in Amritsar district, Punjab, India using machine learning

  • 期刊论文

  • 发表日期：

    2025年5月28日

查看全文
  • Mahesh Chand Singh,
  • Dipakshi Kashyap,
  • Koyel Sur,
  • Vishnu Prasad

摘要

This study presents a comprehensive spatio-temporal analysis and prediction of land use and land cover (LULC) changes in the Amritsar district of Punjab, India, using a Cellular Automata-Artificial Neural Network (CA-ANN) model. Amritsar district has experienced significant land use transformations over the past decades. Satellite images from the years 1990, 2000, 2010, and 2020 were utilized, sourced from the USGS/NASA Landsat Program via Google Earth Engine. The Random Forest classifier was employed for LULC classification, distinguishing between water bodies, agriculture, vegetation, built-up areas, and bare land. Future LULC changes were simulated using the CA-ANN model implemented in QGIS through the MOLUSCE tool. The study observed substantial urban growth at the expense of agricultural and vegetative land, predicting continued urban expansion up to 2050. The findings highlight a 59.0% increase in built-up areas and significant decreases in vegetation (88.1%) and water bodies (47.1%) by 2050. These trends underscore the need for strategic urban planning and sustainable land use practices to mitigate adverse environmental impacts. This research provides critical insights for policymakers and urban planners to ensure balanced development, maintaining ecological integrity alongside economic growth in the Amritsar district.