Detection of Marine Litter on Arctic Beaches Based on Aerial Photography Using the YOLOv8s CNN
Open Access
Abstract
Marine litter beach accumulation is a pressing issue not only for urban coastal areas but also for remote and uninhabited regions such as the Arctic. Existing manual litter collection and identification methods remain labor-intensive. An assessment of the volume and composition of marine litter was conducted for the Russian Arctic coastlines using high-resolution airphotos. The method is based on training the You Only Look Once (YOLOv8, 2023) convolutional neural network (CNN) in the Oriented Bounding Box (OBB) configuration to recognize plastic, metal, fishing gear, wood, and other types of marine litter on images. The best detection performance was obtained for metal and plastic—large, visually contrasting litter items. The worst performance was obtained for wood and other debris, primarily due to their similarity to the natural background. Machine learning (ML) methods combined with remote sensing data represent a new high-precision tool for large-scale environmental monitoring in the Arctic.Keywords
All Related Versions
Funding Information
- the Ministry of Science and Higher Education of the Russian Federation (FSRW-2024-0005)
This publication has 32 references indexed in Scilit:
- A systematic image augmentation framework based on dataset limitations for small object detectionIran Journal of Computer Science, 2026
- Remote Sensing for Monitoring Macroplastics in Rivers: A ReviewWIREs Water, 2025
- A survey of small object detection based on deep learning in aerial imagesArtificial Intelligence Review, 2025
- A Dataset for Detection and Segmentation of Underwater Marine Debris in Shallow WatersScientific Data, 2024
- Beach litter composition, distribution patterns and annual budgets on Novaya Zemlya archipelago, Russian ArcticMarine Pollution Bulletin, 2024
- A review of convolutional neural networks in computer visionArtificial Intelligence Review, 2024
- Development of automated marine floating plastic detection system using Sentinel-2 imagery and machine learning modelsMarine Pollution Bulletin, 2022
- Mapping marine litter with Unmanned Aerial Systems: A showcase comparison among manual image screening and machine learning techniquesMarine Pollution Bulletin, 2020
- Finding Plastic Patches in Coastal Waters using Optical Satellite DataScientific Reports, 2020
- Marine litter pollution on the Northern Island of the Novaya Zemlya archipelagoMarine Pollution Bulletin, 2020