Scholarlink

<p>Land Use and Land Cover (LULC) are used to map the natural features and human activities of a landscape for any given time frame. It is necessary to continuously monitor the changes in LULC for the effective management of natural resources to comprehend the various effects of climate change. The remote sensing techniques is used to explore, map, and monitor landscapes, thus helping to understand the diverse effects of natural and man-made features. This study focuses on using machine learning techniques, particularly supervised algorithms, to extract thematic information from multi spectral satellite images. The main objective of this work is to map the LULC of the Brahmani-Baitarani basin from India using the Random Forest algorithm on remote sensing data collected via Google Earth Engine (GEE). The LULC is classified into four categories: vegetative cover, water bodies, barren land, and urban land, utilizing Sentinel 2, Landsat 8, and Landsat 9 data along with dynamic world cover, and the European Space Agency dataset. This study aims to support decision-makers, planners, and remote sensing experts in accurately performing LULC classification in rapidly urbanizing areas.</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

Evaluation of Random Forest algorithms for mapping of land use land cover using remote sensing data for Baitarani River

  • 期刊论文

  • 发表日期：

    2025年2月11日

查看全文
  • Sonali Kadam,
  • Anjali Kadam,
  • Sae Jamdade,
  • Namrata Rathi,
  • Apurva Gadilkar,
  • Chahal ohri,
  • Jotiram Gujar,
  • Ravindra Kale

摘要

Land Use and Land Cover (LULC) are used to map the natural features and human activities of a landscape for any given time frame. It is necessary to continuously monitor the changes in LULC for the effective management of natural resources to comprehend the various effects of climate change. The remote sensing techniques is used to explore, map, and monitor landscapes, thus helping to understand the diverse effects of natural and man-made features. This study focuses on using machine learning techniques, particularly supervised algorithms, to extract thematic information from multi spectral satellite images. The main objective of this work is to map the LULC of the Brahmani-Baitarani basin from India using the Random Forest algorithm on remote sensing data collected via Google Earth Engine (GEE). The LULC is classified into four categories: vegetative cover, water bodies, barren land, and urban land, utilizing Sentinel 2, Landsat 8, and Landsat 9 data along with dynamic world cover, and the European Space Agency dataset. This study aims to support decision-makers, planners, and remote sensing experts in accurately performing LULC classification in rapidly urbanizing areas.