We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
In-line identification of Pb-based pigments in fishing nets and ropes based on hyperspectral imaging and machine learning
AI summary Read the abstract
Researchers assessed microplastic contamination in drinking water sources across a large river basin, examining both surface water and groundwater at multiple sites. All sampled sources contained microplastics, with surface water generally showing higher concentrations, and fibers were consistently the dominant morphotype across all water types and locations.
Fishing lines, nets, and ropes represent a significant portion of plastic pollution in marine environments, and can contain hazardous additives. The development of less laborious and faster methods aiming at identifying plastic-related additives is therefore needed, in order to facilitate effective recycling. This work aims to develop an industrial inline method to identify lead-based pigments in fishnets by an industrial hyperspectral imaging (HSI) system working in visible-near-infrared spectral range (Vis-NIR, 450 to 1050 nm) and machine learning. A Vis-NIR spectral sample set comprising un-contaminated and lead contaminated (143 to 2430 mg L-1) plastic classes were used to build the classification model via Principal Component Analysis and clustering. The content of the samples was characterized by X-ray fluorescence (XRF), Attenuated Total Reflection (ATR-FTIR), differential scanning calorimetry, thermogravimetric analysis, and burning in astmospheric air. Fishnets containing lead-based pigments with lead concentrations > 1000 mg L-1 (0.1 wt%) were accurately identified by the industrial HSI, and the lead content was corroborated with ATR-FTIR and XRF measurements. In addition, lead contaminated plastic area and mass can be estimated via calibration curve using the pixels numbers vs mass of fibrous plastics with a detectability of 120 mg (R2 = 0.997).
More Papers Like This
A pipeline for meso- and microplastic identification in aquatic systems using machine learning and hyperspectral imaging
AI summary Read the abstract
This study developed an analytical pipeline combining near-infrared hyperspectral imaging (HSI-NIR) with a Multi-Layer Perceptron (MLP) neural network for pixel-wise identification of microplastic polymers in environmental samples from Lanzarote Island, the Wadden Sea, and Rhine/Waal rivers. The MLP model outperformed Support Vector Machines, Random Forests, and PLS-DA in polymer identification, with PE and PP dominant across all sites and higher microplastic concentrations found in the Rhine than the Waal.
Spectrometric Detection Of Microplastics In The Environment: A Novel Approach Using Hyperspectral Imaging System
AI summary Read the abstract
This study developed a novel spectrometric approach to detect microplastics in environmental samples, combining spectral analysis with machine learning classification. The method enabled rapid, accurate identification of multiple polymer types without extensive sample preparation.
An effective strategy for the monitoring of microplastics in complex aquatic matrices: Exploiting the potential of near infrared hyperspectral imaging (NIR-HSI)
AI summary Read the abstract
Researchers developed a near infrared hyperspectral imaging (NIR-HSI) method for rapid monitoring of microplastics in complex marine matrices, demonstrating effective detection and polymer identification that overcomes the time and cost limitations of conventional spectroscopic analysis approaches.
Identificação de microplásticos no ambiente e detecção de impurezas em café por imageamento hiperespectral na região do infravermelho próximo (HSI-NIR) e quimiometria
AI summary Read the abstract
This study applied near-infrared hyperspectral imaging (HSI-NIR) combined with SIMCA chemometric classification to automatically identify microplastics of five polymer types (PE, PP, PA, PET, PS) in beach sand and to detect impurities in roasted coffee. Models built from a comprehensive spectral library covering pure to weathered microplastics achieved over 99% sensitivity and specificity for all polymer classes, validated on hundreds of environmental particles. The approach enables rapid automated identification of thousands of microplastic particles without prior visual sorting, offering substantial efficiency gains over conventional methods.
Development of robust models for rapid classification of microplastic polymer types based on near infrared hyperspectral images
AI summary Read the abstract
Researchers used near-infrared hyperspectral imaging combined with machine learning to classify nine types of microplastic particles, finding reliable results even for small particles on wet filters. This method could enable faster, automated identification of diverse microplastic types in environmental water samples.
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.