Scholarlink

<p>This research used field data, remote sensing data, and machine learning algorithms to evaluate the role and value of trees outside forests. The study was conducted in a tropical region—Thai Nguyen Province, Vietnam. Outstanding results include assessing biodiversity value, use value, timber volume and carbon stock of trees outside forests. This study employed satellite images, including optical (Landsat 8, Landsat 9) and radar (ALOS-2 PALSAR-2) data, to build a model to estimate the carbon storage and timber volume of trees outside forests. The results indicated that optical satellite data explain carbon storage and timber volume reaching up to 69% and 42%, respectively, whereas radar satellite data explain up to 69% and 64%, respectively. The combination of optical and radar satellite data has significantly improved the efficiency of assessing carbon and timber, with mapping accuracies reaching up to 81% and 69%, respectively. The study improves TOF assessment through the integration of field data, satellite imagery, and machine learning, enabling more reliable evaluation and management.</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

Assessing the Role and Value of Trees outside Forests by Integration of Field Plots, Remote Sensing Data, and Machine Learning Algorithms

  • 期刊论文

  • 发表日期：

    2025年11月15日

查看全文
  • Luong Nguyen Viet,
  • Tu To Trong,
  • Son Le Mai,
  • Giang Nguyen Vu

摘要

This research used field data, remote sensing data, and machine learning algorithms to evaluate the role and value of trees outside forests. The study was conducted in a tropical region—Thai Nguyen Province, Vietnam. Outstanding results include assessing biodiversity value, use value, timber volume and carbon stock of trees outside forests. This study employed satellite images, including optical (Landsat 8, Landsat 9) and radar (ALOS-2 PALSAR-2) data, to build a model to estimate the carbon storage and timber volume of trees outside forests. The results indicated that optical satellite data explain carbon storage and timber volume reaching up to 69% and 42%, respectively, whereas radar satellite data explain up to 69% and 64%, respectively. The combination of optical and radar satellite data has significantly improved the efficiency of assessing carbon and timber, with mapping accuracies reaching up to 81% and 69%, respectively. The study improves TOF assessment through the integration of field data, satellite imagery, and machine learning, enabling more reliable evaluation and management.