We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Deliverable 10. AI Methods for MNP Research - A Roadmap for the Possible Applications of Artificial Intelligence Methods in Micro and Nano-Plastics Research
AI summary Read the abstract
This deliverable from the MOMENTUM research project provided a roadmap for applying AI methods—including deep learning, natural language processing, and predictive modeling—to micro- and nanoplastic (MNP) research challenges. The authors identified AI-assisted detection, environmental fate modeling, and exposure-health outcome linkage as the highest-priority applications for accelerating MNP science.
Micro- and nanoplastics (MNPs) have become a critical concern in environmental science and human health. They have been detected in virtually every ecosystem, from the peaks of Mount Everest to the depths of the Mariana Trench, and in diverse organisms, including humans. Their ubiquity raises serious questions about ecological impacts and long-term health risks. Reliable detection and characterisation of MNPs, however, remains highly challenging. Unlike conventional analytes, MNPs represent a vast diversity of polymer types, sizes, shapes, degradation states, and chemical additives (ISO/TR 21960:2020; ISO 24187:2023). To properly characterise them, multiple particle attributes must be assessed simultaneously, often requiring complex workflows involving sample collection, preparation, and analysis. Each stage introduces biases and uncertainties that complicate comparability across studies.
More Papers Like This
Deliverable 10. AI Methods for MNP Research - A Roadmap for the Possible Applications of Artificial Intelligence Methods in Micro and Nano-Plastics Research
AI summary Read the abstract
This deliverable from the MOMENTUM research project provided a roadmap for applying AI methods—including deep learning, natural language processing, and predictive modeling—to micro- and nanoplastic (MNP) research challenges. The authors identified AI-assisted detection, environmental fate modeling, and exposure-health outcome linkage as the highest-priority applications for accelerating MNP science.
AI‐Driven Technologies in Mitigation of Microplastic Pollution
AI summary Read the abstract
Researchers reviewed how AI-assisted detection methods address the accuracy, efficiency, and cost limitations of traditional microplastic identification, while also surveying how artificial intelligence is being applied to model and mitigate microplastic impacts on marine ecosystems and human health including metabolic and respiratory effects.
The Road Ahead
AI summary Read the abstract
Researchers analyzed a decade of AI applications in microplastic detection and found a tenfold increase in related research from 2015 to 2024, with AI systems reaching 94% detection precision versus 72% for traditional microscopy, while also demonstrating the potential of predictive modeling to estimate pollution costs and identify major sources such as synthetic textiles and tire particles.
Introduction to Microplastic and the Role of AI
AI summary Read the abstract
Researchers reviewed how AI methods — including machine learning, deep learning, and IoT-integrated real-time monitoring — are transforming microplastic detection, classification, and pollution mapping, while identifying persistent challenges around data availability, computational cost, and the need for explainable models.
Machine LearningAdvancements and Strategies in Microplasticand Nanoplastic Detection
AI summary Read the abstract
This systematic review summarizes how machine learning technology is being used to detect microplastics and nanoplastics in the environment. Better detection methods are important because understanding where these particles are and how much is present is the first step toward assessing risks to human health.
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.