Scholarlink

<p>The Great Otis Hurricane, which struck Acapulco’s coast on October 25, 2023, caused devastating destruction and caused a significant amount of marine debris. This study estimates the extent of this debris, with an emphasis on plastic debris, based on an analysis of the dispersion of debris using multi-sensor remote sensing and machine learning analysis. On October 24 (pre-hurricane) and 27, MODIS and ASTER satellite data showed the debris footprint of the Hurricane, and machine learning models as well as the Floating Debris Index (FDI) were used to classify debris type on the ocean surface. Classification with the utilization of these technologies can be used to facilitate waste disposal and classification between plastics and natural “debris.” While analysis was very useful, the high-resolution imagery from ASTER unveiled several details from MODIS as its moderate resolution captured the overall extent of impacts due to marine debris. The analysis indicated that large debris clusters were beginning to collect in certain ocean basins, many of which raised concerns about larger environmental issues from large masses of marine debris. The results of the study demonstrate the suitability of remote sensing together with machine learning tools for post-disaster monitoring of twice-deployed environments, and especially marine debris. Consequentially, the need for clean-up action, together with future policy action, continues to be evident to sort target marine debris in the event of extreme weather occurrences.</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

Marine Debris Assessment Post-Hurricane Using Remote Sensing and Machine Learning Techniques

  • 期刊论文

  • 发表日期：

    2025年10月30日

查看全文
  • S. Venkatraman,
  • V. Mohan,
  • Eatedal Alabdulkreem,
  • Achraf Ben Miled,
  • Khalid Nazim Abdul Sattar,
  • Setu Garg

摘要

The Great Otis Hurricane, which struck Acapulco’s coast on October 25, 2023, caused devastating destruction and caused a significant amount of marine debris. This study estimates the extent of this debris, with an emphasis on plastic debris, based on an analysis of the dispersion of debris using multi-sensor remote sensing and machine learning analysis. On October 24 (pre-hurricane) and 27, MODIS and ASTER satellite data showed the debris footprint of the Hurricane, and machine learning models as well as the Floating Debris Index (FDI) were used to classify debris type on the ocean surface. Classification with the utilization of these technologies can be used to facilitate waste disposal and classification between plastics and natural “debris.” While analysis was very useful, the high-resolution imagery from ASTER unveiled several details from MODIS as its moderate resolution captured the overall extent of impacts due to marine debris. The analysis indicated that large debris clusters were beginning to collect in certain ocean basins, many of which raised concerns about larger environmental issues from large masses of marine debris. The results of the study demonstrate the suitability of remote sensing together with machine learning tools for post-disaster monitoring of twice-deployed environments, and especially marine debris. Consequentially, the need for clean-up action, together with future policy action, continues to be evident to sort target marine debris in the event of extreme weather occurrences.