Deep learning for detecting macroplastic litter in water bodies: A review. (1st March 2023)

• Record Type: Journal Article
• Authors: Jia, Tianlong; Kapelan, Zoran; de Vries, Rinze; Vriend, Paul; Peereboom, Eric Copius; Okkerman, Imke; Taormina, Riccardo
• Is Part Of: Water research. Volume 231(2023)
• Publication Date: 2023-03-01
• Subjects: Artificial intelligence -- Computer vision -- Environmental monitoring -- Neural networks -- Macroplastics -- Pollution; AE Artificial environment -- AI Artificial intelligence -- AUV Autonomous underwater vehicle -- CNN Convolutional neural network -- COCO Common Objects in Context -- CV Computer vision -- DA Data augmentation -- DL Deep learning -- DSGC Device setup generalization capability -- EGC Environmental generalization capability -- GGC Geographical generalization capability -- IC Image classification -- IoU Intersection over union -- IS Image segmentation -- mAP mean average precision -- ML Machine learning -- MLOps Machine learning operations -- MLP Multilayer Perceptron -- NGC Non-aquatic generalization capability -- OA Overall accuracy -- OD Object detection -- OSPAR Oslo and Paris Conventions -- ROV Remotely operated vehicle -- TL Transfer learning -- UAV Unmanned aerial vehicle; Water -- Pollution -- Research -- Periodicals; 363.7394
• DOI: 10.1016/j.watres.2023.119632
• Languages: English
• ISSNs: 0043-1354

Abstract

Highlights: We review studies on deep learning (DL) for detecting macroplastics in water bodies. Studies disregard the importance of riverine macroplastic litter. There is a lack of DL-based detection models with robust generalization capability. DL-based quantification of macroplastic (mass) fluxes and hotspots is lacking. We are lacking DL-based structural monitoring strategies. Abstract: Plastic pollution in water bodies is an unresolved environmental issue that damages all aquatic environments, and causes economic and health problems. Accurate detection of macroplastic litter (plastic items >5 mm) in water is essential to estimate the quantities, compositions and sources, identify emerging trends, and design preventive measures or mitigation strategies. In recent years, researchers have demonstrated the potential of computer vision (CV) techniques based on deep learning (DL) for automated detection of macroplastic litter in water bodies. However, a systematic review to describe the state-of-the-art of the field is lacking. Here we provide such a review, and we highlight current knowledge gaps and suggest promising future research directions. The review compares 34 papers with respect to their application and modeling related criteria. The results show that the researchers have employed a variety of DL architectures implementing different CV techniques to detect macroplastic litter in various aquatic environments. However, key knowledge gaps must be addressed to overcome the lack of: (i) DL-based macroplastic litter detection models with sufficient generalization capability, (ii) DL-based quantification of macroplastic (mass) fluxes and hotspots and (iii) scalable macroplastic litter monitoring strategies based on robust DL-based quantification. We advocate for the exploration of data-centric artificial intelligence approaches and semi-supervised learning to develop models with improved generalization capabilities. These models can boost the development of new methods for the quantification of macroplastic (mass) fluxes and hotspots, and allow for structural monitoring strategies that leverage robust DL-based quantification. While the identified gaps concern all bodies of water, we recommend increased efforts with respect to riverine ecosystems, considering their major role in transport and storage of litter. Graphical abstract: Image, graphical abstract