We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Deep learning-powered efficient characterization and quantification of microplastics
Summary
Researchers developed an artificial intelligence framework that uses deep learning to automatically identify and quantify microplastics from infrared spectra and visual images. The system achieved high accuracy in classifying plastic types and counting particles, dramatically reducing the time needed compared to manual analysis. This tool could make large-scale microplastic monitoring faster and more consistent across different research laboratories.
Characterizing and quantifying microplastics (MPs) are time-consuming and labor-intensive tasks traditionally. This paper presents an artificial intelligence (AI) framework aiming to automate these tasks by integrating computer vision and deep learning techniques. The approach leverages Fourier Transform Infrared (FTIR) spectra and visual images. Primary novelties of this research involve the development of: (1) an AI framework integrating efforts of data processing, analytics, visualization, and human-computer interaction; (2) a method for transforming FTIR data into contour images; (3) data augmentation strategies for resolving data scarcity and imbalance issues; (4) deep learning models for identifying MPs; (5) computer vision algorithms for quantifying MPs; and (6) an engineer-friendly graphic user interface (GUI) for enhancing data accessibility. The AI framework has been applied to polyethylene, polypropylene, polystyrene, polyamide, ethylene-vinyl acetate, and cellulose acetate. Results confirmed the efficacy of the framework, exhibiting high accuracy scores in classification (98 %), segmentation (99 %), and quantification (96 %) tasks. This research advances the capability of automatic assessment of MPs.
Sign in to start a discussion.
More Papers Like This
PlasticNet: Deep Learning for Automatic Microplastic Recognition via FT-IR Spectroscopy
Researchers developed PlasticNet, a deep learning algorithm that automatically identifies microplastic types from infrared spectral data, outperforming conventional library matching approaches. Automating microplastic identification could dramatically speed up the analysis of environmental samples and reduce human error.
Automated Machine-Learning-Driven Analysis of Microplastics by TGA-FTIR for Enhanced Identification and Quantification
Researchers developed an automated machine-learning system to identify and measure microplastics using a combination of heat analysis and infrared spectroscopy. The system can distinguish between different plastic types more accurately and faster than manual methods. Better detection tools like this are important because reliable measurement of microplastics in food, water, and the environment is essential for understanding human exposure levels.
Detection of Microplastics Using Machine Learning
Researchers reviewed and demonstrated machine learning approaches for detecting and classifying microplastics in environmental samples, finding that automated image analysis and spectral classification methods can improve the speed and accuracy of microplastic monitoring compared to manual methods.
A Deep Learning Approach for Microplastic Segmentation in Microscopic Images
Researchers developed a deep learning model for automated segmentation and classification of microplastics in microscopic images, identifying five distinct categories including fibers, fragments, spheres, foam, and film. The model achieved high accuracy while maintaining low computational requirements, making it suitable for high-throughput deployment in environmental monitoring. The study offers a tool that could help overcome the measurement bottleneck in microplastic characterization for toxicological and risk assessment studies.
Machine learning outperforms humans in microplastic characterization and reveals human labelling errors in FTIR data
Researchers developed a small but powerful neural network that can identify microplastic types from infrared spectroscopy data more accurately than human experts. The AI model classified 16 different categories of microplastics and even revealed errors in human-labeled data. This technology could dramatically speed up microplastic analysis in environmental and health studies, making it easier to understand the scale and types of microplastic contamination people are exposed to.