We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Analysis of microplastics and nanoplastics emerged from polyethylene bags and polyethylene terephthalate bottles by an artificial intelligence-enabled tool
AI summary Read the abstract
Researchers subjected polyethylene bags and PET bottles to 12 weeks of simulated mechanical and photodegradation and used an AI-enabled annotation tool (FastSAM) to characterize the resulting micro- and nanoplastic particles by count, size, and morphology, finding PET generated far more particles than PE.
This study presents a comprehensive and comparative analysis of the emergence of micro- and nanoplastics (MNPs) from polyethylene (PE) plastic bags and polyethylene terephthalate (PET) water bottles. We subjected these polymers to simulated mechanical and photodegradation conditions in an isolated chamber for 12 weeks to understand their environmental implications and degradation mechanisms. We analyzed 614 and 3924 plastic particles that emerged from PE and PET, respectively, using an artificial intelligence (AI) enhanced automatic annotation tool (FastSAM) focusing on MNPs' particle count, size distribution, and morphology. This innovative approach combines comprehensive simulation of environmental conditions with AI-enabled image analysis, providing detailed insight into the relative contributions of PE and PET products to plastic pollution. Our findings indicate that PET fragments more readily into smaller particles, with a higher proportion of nanoplastics (57.6 %) than PE (24.9 %). The concentration of the emerged particles was found to be 4.17 million particles/L (0.07 ppm) for PE and 27.8 million particles/L (0.18 ppm) for PET. Characterization techniques, including dynamic light scattering (DLS), scanning electron microscopy (SEM), Fourier-transform infrared spectroscopy (FTIR), and X-ray photoelectron spectroscopy (XPS) were used to examine both bulk plastics and the MNPs that emerged from them.
More Papers Like This
Environmental degradation of consumer plastics into microplastics and nanoplastics and their classification using machine learning
AI summary Read the abstract
Researchers studied the environmental degradation of three common consumer plastics — low-density polyethylene shopping bags, polyethylene terephthalate water bottles, and take-food trays — under UV radiation, abrasion, atmospheric oxidation, and freeze-thaw cycles, then applied machine learning algorithms to classify the resulting microplastic and nanoplastic particles.
Environmental degradation of consumer plastics into microplastics and nanoplastics and their classification using machine learning
AI summary Read the abstract
Researchers studied the environmental degradation of consumer plastics — LDPE shopping bags, PET water bottles, and take-food trays — under UV radiation, abrasion, atmospheric oxidation, and freeze-thaw cycles, then trained and applied machine learning classifiers to identify and categorize the resulting microplastic and nanoplastic particles.
Morphological Detection and Classification of Microplastics and Nanoplastics Emerged from Consumer Products by Deep Learning
AI summary Read the abstract
Researchers created a new open-source dataset of microscopy images for training AI models to automatically detect and classify micro- and nanoplastics. The dataset fills an important gap in available tools for microplastic research and provides a foundation for developing faster, more efficient methods to identify plastic contamination across environmental samples.
Experimental investigations on polyethylene and polyethylene terephthalate microplastics’ degradation. A review
AI summary Read the abstract
Researchers conducted experiments to study the physical and chemical behavior of polyethylene and PET microplastic particles under different environmental conditions. The study contributes to understanding how these plastics persist and transform in the environment.
A Fully Automated YOLO-SAM Framework for High-Precision Microplastic Analysis in Environmental Sample
AI summary Read the abstract
Researchers built an automated computer program that combines two AI tools to detect and outline microplastic particles in microscope images. Tested on 5,653 images, the fully automatic system matched particle shapes accurately, and performed even better when given some manual guidance, outperforming an existing method by more than 22%.
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.