We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
An Alternative 2D Shape Descriptor Index for Rapid Prediction of Microplastics Morphology Using Deep Feature Embeddings and Machine Learning
AI summary Read the abstract
This study detected microplastics in livestock feed and fodder, measuring plastic particle contamination in materials used for animal production. The findings raise concerns about microplastic transfer through animal agriculture into meat, milk, and eggs consumed by humans.
ABSTRACT Microplastic morphology influences particle behavior, environmental fate, and ecological risk, yet commonly used two‐dimensional (2D) shape descriptors often struggle to represent complex and irregular geometries. This study introduces the Shape Descriptor Index (SDI), a composite metric integrating area, length, and circularity, designed as an alternative and machine‐compatible proxy for microplastic morphology. Using deep feature embeddings extracted from scanning electron microscopy (SEM) images with Inception V3, we evaluated the predictability of SDI relative to classical descriptors across multiple machine learning models. SDI demonstrated the strongest performance, particularly with the AdaBoost model, achieving an R 2 of 0.919 along with reduced root mean square error (RMSE) and mean absolute percentage error (MAPE) compared to the other descriptors. These findings indicate that SDI aligns well with deep visual representations and offers a robust, scalable metric for rapid morphology assessment. The approach supports high‐throughput and objective analysis, making SDI particularly suitable for large‐scale environmental monitoring and automated microplastic characterization.
More Papers Like This
Identification of Microplastics in Soils Using 2D Geometric Shape Descriptors
AI summary Read the abstract
Researchers applied 2D geometric shape descriptors and Random Forest machine learning to distinguish microplastic particles from soil particles in microscopy images. The results demonstrated promising potential for automated microplastic identification in soil samples, which are more challenging to analyze than water samples.
Automatic quantification and classification of microplastics in scanning electron micrographs via deep learning
AI summary Read the abstract
Researchers developed a deep learning system that can automatically detect and classify microplastics in scanning electron microscope images, replacing the time-consuming process of manual analysis. The system achieved high accuracy in identifying different types and shapes of microplastic particles, even very small ones that are difficult to spot by eye. This automated approach could significantly speed up microplastic monitoring and pollution assessment efforts.
Deep Learning-Based Shape Classification for Hyperspectral-Imaged Microplastics
AI summary Read the abstract
Researchers tested nine deep learning architectures for automating the shape classification of microplastic particles in hyperspectral images, comparing performance on original and augmented datasets. The best models achieved high classification accuracy, offering a faster and more consistent alternative to labour-intensive manual identification.
Deep learning based approach for automated characterization of large marine microplastic particles
AI summary Read the abstract
A deep learning approach using Mask R-CNN was trained on 3,000 images of marine microplastic particles to automatically locate, classify, and segment particles by shape categories including fiber, fragment, pellet, and rod. The model achieved high accuracy and outperformed manual visual inspection for characterizing large marine microplastic datasets.
Defining Irregular Microplastics: A Machine Learning Approach for Morphometric Characterization
AI summary Read the abstract
Researchers applied a machine learning decision-tree classifier to hyperspectral images of 129 nano- and microplastic particles and identified five morphometric descriptors—circularity, roundness, solidity, long diameter, and perimeter-area ratio—that together distinguish irregular particles from spherical and fibrous forms with 96% accuracy, providing a standardized definition for the most environmentally prevalent but least-defined shape class.
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.