We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
An integrated spectral library and analysis workflow for laboratory identification of microplastic polymers
AI summary Read the abstract
Researchers built a reference library of light-reflectance measurements for six common plastic types, plus a software tool to compare and identify unknown microplastic samples based on these patterns. Testing showed the method correctly identified polymer type about 65% of the time and particle size category about 36% of the time.
Abstract Microplastics are an increasing environmental concern, and their reliable identification requires fast, reproducible, and non-destructive analytical approaches. This study presents a reflectance spectral library and a dedicated software tool, the Microplastic Spectral Analysis App version 3.1, for organizing, visualizing, comparing, and classifying microplastic spectra. The library contains reflectance spectra polyethylene terephthalate, high-density polyethylene, polyvinyl chloride, low-density polyethylene, polypropylene, and polystyrene measured across the visible, near-infrared, and short-wave infrared range under controlled laboratory conditions. The samples represented multiple nominal sieve fractions and selected colours. Spectral profiles showed descriptive differences associated with polymer type, nominal sieve fraction, and colour. Principal component analysis was used to visualize polymer-related grouping patterns among transparent samples. In group-level cross-validation, the support vector machine provided the best polymer-type classification, with an out-of-fold accuracy of 0.649, whereas the random forest provided the best nominal sieve-fraction classification, with an out-of-fold accuracy of 0.355. The library and software provide an integrated framework for organizing and reusing laboratory microplastic reflectance spectra.
More Papers Like This
Machine learning based workflow for (micro)plastic spectral reconstruction and classification
AI summary Read the abstract
A machine learning pipeline combining two spectral reconstruction models with four classification algorithms can identify microplastic polymer types from spectral data with up to 98% accuracy on processed spectra. Applied to real environmental samples, the best model achieved 71% top-one accuracy and over 90% top-three accuracy. Automated, high-accuracy microplastic identification tools are critical for scaling up environmental monitoring and making large-scale surveys practical.
A comparison of microscopic and spectroscopic identification methods for analysis of microplastics in environmental samples
AI summary Read the abstract
Researchers compared microscopic and spectroscopic methods for analyzing microplastics in environmental samples, evaluating accuracy and efficiency and finding that spectroscopic confirmation substantially reduces misidentification errors.
Spectroscopic Identification of Environmental Microplastics
AI summary Read the abstract
Scientists developed a machine learning classifier that identifies the chemical type of environmental microplastic samples from spectral data with over 97% accuracy, even for samples from unknown sources. Automated spectral identification tools are critical for scaling up microplastic monitoring across large environmental datasets.
Identification and morphological characterization of different types of plastic microparticles
AI summary Read the abstract
Researchers used multiple complementary techniques to identify and characterize the morphology and polymer composition of different types of plastic microparticles. They compared methods including optical microscopy, scanning electron microscopy, and spectroscopic analysis to evaluate their reliability. The study provides practical guidance for standardizing microplastic identification protocols, which is important for producing comparable results across different research laboratories.
Automatic microplastic classification using dual-modality spectral and image data for enhanced accuracy
AI summary Read the abstract
A dual-modality classification system combining FTIR spectral data and microscope images achieved 99% accuracy in automatically identifying five common microplastic polymer types. The study deployed a web application (MPsSpecClassify) that enables researchers to efficiently classify microplastics, addressing the time-consuming and error-prone nature of manual spectral analysis.
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.