0
Review Sign in to save

Emerging AI Solutions for Hazardous PET Waste in Marine Environments: A Review of Underexplored Paradigms

2025

AI summary Read the abstract

This review surveys emerging and underexplored AI technologies — including reinforcement learning, federated learning, generative AI, and edge computing — for managing PET plastic pollution in marine environments, identifying conceptual gaps and proposing these approaches as next-generation tools for real-time monitoring, autonomous collection, and intelligent biodegradation systems.

Polymers

Polyethylene terephthalate (PET) pollution, due to its persistence, chemical recalcitrance, and widespread usage, represents a growing hazard to marine ecosystems. Its accumulation contributes to long-term ecotoxicological risks, food chain contamination, and environmental degradation. Addressing this challenge necessitates the adoption of scalable, efficient, and intelligent strategies for monitoring, collection, and degradation. While artificial intelligence (AI) has shown promise—particularly through machine learning (ML), deep learning (DL), and computer vision (CV)—these approaches have already been extensively covered in recent reviews and are therefore beyond the scope of this research. Instead, this article focuses on underexplored and emerging AI technologies with untapped potential in marine PET management. These include reinforcement learning, generative AI, Edge AI, soft robotics, federated learning, explainable AI, decision support systems, and large multimodal models (LMMs). These technologies offer new capabilities for real-time decision-making, distributed data processing, autonomous biodegradation, and intelligent system design—critical tools in managing hazardous waste scenarios—yet remain largely absent from current PET-focused research. We synthesize existing literature where applicable—such as in reinforcement learning, Edge AI, and soft robotics—while also investigating areas where research is still sparse or speculative, such as federated learning and LMMs. This addresses the need for a comprehensive review that not only maps current applications but also identifies conceptual gaps where emerging AI technologies can drive future innovation. Through a bibliometric analysis of leading scientific databases and a thematic synthesis of technological trajectories, this article straddles the line between a traditional review and a forward-looking conceptual overview. It aims to inform researchers, inspire interdisciplinary collaboration, and advance sustainable, hazard-mitigating solutions for marine PET management in a rapidly evolving technological landscape.

More Papers Like This

Article

AI-Integrated Chemistry Solutions for Sustainable Plastic Waste Management

AI summary Read the abstract

This paper reviews how artificial intelligence is being applied to improve plastic waste recycling efficiency, expand recycling technologies, and support development of biodegradable plastic alternatives. Real-world case studies illustrate AI's potential to transform plastic waste management and advance sustainable solutions.

Article

The Diversity of Artificial Intelligence Applications in Marine Pollution: A Systematic Literature Review

AI summary Read the abstract

This systematic literature review analyzed AI applications for marine pollution management from Web of Science and Scopus databases, finding that 57% target monitoring, 24% management, and 19% prediction. The review identifies oil spill detection, water quality monitoring, and plastic identification as the three major application areas where AI offers the greatest capabilities.

Article Tier 2

Artificial intelligence for modeling and reducing microplastic in marine environments: A review of current evidence

AI summary Read the abstract

This review examines how artificial intelligence is being applied to address marine microplastic pollution, including modeling accumulation zones, developing real-time detection systems using remote sensing and robotics, and creating AI-based filtration technologies. The study suggests that while AI holds significant promise for predicting microplastic flows and supporting targeted cleanup efforts, challenges remain around data availability, model refinement, and international collaboration.

Article

A study on AI solutions for plastic degradation, its benefits, and challenges

AI summary Read the abstract

This review surveys how artificial intelligence and machine learning tools are being applied to accelerate the discovery and optimization of plastic-degrading processes, including enzyme engineering and biodegradation pathway modeling. It highlights the potential for AI to significantly shorten the timeline from laboratory discovery to scalable plastic breakdown solutions.

Review

Application of Machine Learning in Plastic Waste Detection and Classification: A Systematic Review

AI summary Read the abstract

This systematic review of 56 studies finds that machine learning models — particularly convolutional neural networks — can detect and classify plastic waste with accuracy frequently exceeding 80%, supporting the potential of AI to improve plastic waste management practices.

Research digests by email

When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.

Email me about

Share this paper