Artificial Intelligence in Ocean Clean-Up: Deep Learning Approaches to Marine Litter Detection

Abstract

Marine litter contamination causes a tremendous environmental issue with a high influence on the consequences for ocean ecosystems and human societies. This study offers a concise overview of the impacts, potential solutions, and causes to address this complex problem with Artificial Intelligence. The sources of marine pollution encompass a wide range of human activities, including oil spills, chemical discharges, plastic waste, nutrient runoff, sewage disposal, and atmospheric deposition. These pollutants pose significant threats to marine life, biodiversity, and ecosystem health. While deep learning technologies have shown promise in various environmental applications, including pollution monitoring and management, their direct application to solving marine pollution is limited. Deep learning algorithms can be used to analyze images and video footage from drones or underwater cameras to identify and track plastic pollution. This study additionally provides debris analysis utilizing publicly available datasets generated by a few studies. The several approaches that are being considered can be applied to the creation and efficient management of litter in the future, preserving our ecology. Collaborative efforts between environmental scientists, engineers, and data scientists are crucial to developing robust and effective deep-learning solutions for marine pollution management.