Scholarlink

For sustainable urban development globally, it is essential to monitor human-induced changes and develop reliable and methodologically consistent urban area maps. In GHSL, multispectral satellite images are segmented using symbolic machine learning (SML) to produce reliable and automated maps of built-up areas. Experiments conducted on the benchmark Landsat-8 dataset demonstrated SML's accurate classification of large satellite images. Large datasets were measured with high accuracy using both simple and quantum-entanglement-free kernels.

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

Multispectral Satellite Image Classification Using Symbolic Machine Learning for Land Cover Area and Land Cover

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Mohammed Ridha Hammoodi,
  • Ali Ashoor Issa

摘要

For sustainable urban development globally, it is essential to monitor human-induced changes and develop reliable and methodologically consistent urban area maps. In GHSL, multispectral satellite images are segmented using symbolic machine learning (SML) to produce reliable and automated maps of built-up areas. Experiments conducted on the benchmark Landsat-8 dataset demonstrated SML's accurate classification of large satellite images. Large datasets were measured with high accuracy using both simple and quantum-entanglement-free kernels.