Scholarlink

The aim of this paper is to provide a comprehensive review, based on recently published papers and compare information regarding Above-ground biomass modelling, data sources, methodology, and model accuracy. To fulfill the objectives of the INNO4CFIs project and as an output of this study, we propose utilizing high-resolution surface reflectance data acquired from commercial satellites for index and feature derivation. Integrating Digital Surface Models and Digital Terrain Models derived from Light Detection and Ranging, or Synthetic Aperture Radar (SAR) data, enhances the accuracy of biomass prediction. The Random forest model excels in incorporating multiple features, thus adeptly capturing sample characteristics.

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

The Use of High-Resolution Satellite Imagery and Artificial Intelligence for Above-Ground Biomass Modelling in the Mediterranean Region: A Review

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ramadhan Ramadhan,
  • Thijs Koop,
  • Federico Franciamore,
  • Tina Nikaein,
  • Lorenzo Scatena,
  • Eleonora Lombardi,
  • Valerio Roscani

摘要

The aim of this paper is to provide a comprehensive review, based on recently published papers and compare information regarding Above-ground biomass modelling, data sources, methodology, and model accuracy. To fulfill the objectives of the INNO4CFIs project and as an output of this study, we propose utilizing high-resolution surface reflectance data acquired from commercial satellites for index and feature derivation. Integrating Digital Surface Models and Digital Terrain Models derived from Light Detection and Ranging, or Synthetic Aperture Radar (SAR) data, enhances the accuracy of biomass prediction. The Random forest model excels in incorporating multiple features, thus adeptly capturing sample characteristics.