Scholarlink

The increasing complexity of Earth Observation (EO) datasets has resulted in a significant change in the way environmental data are analyzed. Traditional desktop-based EO dataset analyzing platforms and tools, although effective, often lag due to their limited computational capabilities and storage space. However, the advent of web-based EO dataset analyzing tools and platforms like Google Earth Engine (GEE), with large, multi-petabyte storage capacity and access to multi-dimensional datasets has helped overcome these shortcomings (Roy and Chintalacheruvu in Earth Sci Inf 17(1):501–526, 2024). Yet even these tools alone are incapable of covering all aspects of EO dataset analysis and hence require the incorporation of ML algorithms to fully and holistically support environmental monitoring using EO dataset.

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

Machine Learning for Earth Observation

  • 章节

  • 发表日期：

    2026年

查看全文
  • Srija Roy,
  • Manish Kumar Goyal

摘要

The increasing complexity of Earth Observation (EO) datasets has resulted in a significant change in the way environmental data are analyzed. Traditional desktop-based EO dataset analyzing platforms and tools, although effective, often lag due to their limited computational capabilities and storage space. However, the advent of web-based EO dataset analyzing tools and platforms like Google Earth Engine (GEE), with large, multi-petabyte storage capacity and access to multi-dimensional datasets has helped overcome these shortcomings (Roy and Chintalacheruvu in Earth Sci Inf 17(1):501–526, 2024). Yet even these tools alone are incapable of covering all aspects of EO dataset analysis and hence require the incorporation of ML algorithms to fully and holistically support environmental monitoring using EO dataset.