Multispectral Satellite Imaging for Detection and Quantification of Floating Coastal Macro-Litter

Floating plastic waste threatens marine ecosystems, human health, and global sustainability, impacting over 900 aquatic species and incurring economic losses of ${\$}$6-19 billion annually. Effective monitoring is critical yet challenging due to the vastness of aquatic environments. This study introduces an automated, deep learning-based framework for detecting and mapping floating macro-litter along the Karachi coast using highresolution multispectral satellite imagery from PRSS-1 and WorldView-3 ($0.7-3 \mathrm{~m} / \mathrm{pixel}$). Unlike UAV-dependent methods, our satellite-only approach ensures scalability across coastal and inland waters. The pipeline employs YOLOv12, YOLOv4-Tiny, and Faster R-CNN, trained on 10,000 annotated images under diverse water conditions. YOLOv12 achieves a precision of $0.95, \mathrm{mAP}$ of 0.88, and F1score of 0.91, with an inference speed of 2 ms per image. Validated with UAV imagery, the framework supports realtime, large-scale monitoring over $1,000 \mathrm{~km}^{2}$, enabling early detection and cost-effective mitigation. This scalable solution advances global plastic pollution monitoring, offering a robust tool for environmental protection and policymaking.

• Publication year

  2025

• Venue

  2025 IEEE International Workshop on Metrology for the Sea; Learning to Measure Sea Health Parameters (MetroSea)

• Publication date

  2025-10-08

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/MetroSea66681.2025.11245702
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• FreqDyn-YOLO: A High-Performance Multi-Scale Feature Fusion Algorithm for Detecting Plastic Film Residues in Farmland

  2025cited by this paper
• Plastic Waste Over the Ocean: An Approach to Surface Recognition

  2024cited by this paper
• Assessing the detection of floating plastic litter with advanced remote sensing technologies in a hydrodynamic test facility

  2024cited by this paper
• Acoustic signature of plastic marine debris mimics the prey items of deep-diving cetaceans.

  2024cited by this paper
• Crack Detection on Civil Structure Using Efficient Image Processing and Computer Vision Approach

  2024cited by this paper
• Detection of marine floating plastic using Sentinel-2 imagery and machine learning models

  2021cited by this paper
• Finding Plastic Patches in Coastal Waters using Optical Satellite Data

  2020cited by this paper
• Detection of floating plastics from satellite and unmanned aerial systems (Plastic Litter Project 2018)

  2019cited by this paper
• Evidence that the Great Pacific Garbage Patch is rapidly accumulating plastic

  2018cited by this paper
• Interactions of microplastic debris throughout the marine ecosystem

  2017cited by this paper
• Plastic waste inputs from land into the ocean

  2015cited by this paper
• Deleterious Effects of Litter on Marine Life

  2015cited by this paper
• The impact of debris on marine life.

  2015cited by this paper
• Plastics and Human Health

  2012cited by this paper

• No citing papers are available for this paper.