4.8 Article

Spectral Classification of Large-Scale Blended (Micro)Plastics Using FT-IR Raw Spectra and Image-Based Machine Learning

Related references

Note: Only part of the references are listed.
Article Engineering, Environmental

Assessing microplastic characteristics in bottled drinking water and air deposition samples using laser direct infrared imaging

Jenny Nizamali et al.

Summary: There is an urgent need for data on microplastics in uptake media relevant to humans. Laser Direct Infra-Red (LDIR) spectroscopy was used in this study to rapidly analyze microplastics larger than 10 um in bottled drinking water and air samples. The study found high concentrations of microplastics in water bottles and high deposition rates in laboratory and household rooms. The study also identified a significant positive relationship between the surface area of textiles and microplastic deposition.

JOURNAL OF HAZARDOUS MATERIALS (2023)

Article Environmental Sciences

Training and evaluating machine learning algorithms for ocean microplastics classification through vibrational spectroscopy

Henrique de Medeiros Back et al.

Summary: This study compares different classification models and finds that the Support Vector Machine Classifier performs well in quickly and automatically characterizing microplastics in the ocean, striking a good balance between simplicity and performance.

CHEMOSPHERE (2022)

Article Geosciences, Multidisciplinary

Characterization of microplastics in sediment using stereomicroscopy and laser direct infrared (LDIR) spectroscopy

Yi-Ling Cheng et al.

Summary: In this study, the analysis of microplastics in sediment using laser direct infrared imaging was performed. The results showed a significant amount of microplastic particles in the sediment samples, mainly as fragments, and non-plastic micro-sized particles were also identified. The study also discussed the challenges and uncertainties associated with this technique.

GONDWANA RESEARCH (2022)

Article Engineering, Environmental

Flotation separation of hazardous polyvinyl chloride towards source control of microplastics based on selective hydrophilization of plasticizer-doping surfaces

Yingshuang Zhang et al.

Summary: This study proposes a novel scheme for the flotation separation of PVC plastics with different plasticizer contents by regulating hydrophilicity based on selective ferric deposition. By adjusting the ferric concentration, rigid and flexible PVCs can be separated, providing a new method for the recycling of waste PVC plastics.

JOURNAL OF HAZARDOUS MATERIALS (2022)

Article Environmental Sciences

Automatic quantification and classification of microplastics in scanning electron micrographs via deep learning

Bin Shi et al.

Summary: This paper presents a study on the quantification and classification of microplastics using scanning electron microscopy and deep learning methods. The use of deep learning models allows for fast and accurate segmentation and classification of microplastics, which is cheaper and more efficient compared to traditional methods. This research is important for monitoring and evaluating microplastic pollution and investigating potential health risks.

SCIENCE OF THE TOTAL ENVIRONMENT (2022)

Article Engineering, Environmental

Computer-Assisted Analysis of Microplastics in Environmental Samples Based on μFTIR Imaging in Combination with Machine Learning

Benedikt Hufnagl et al.

Summary: This passage expresses gratitude towards various institutions and departments for their funding and support towards research projects, as well as acknowledging the fruitful discussions and critical questions from working groups and standards committees.

ENVIRONMENTAL SCIENCE & TECHNOLOGY LETTERS (2022)

Article Chemistry, Analytical

Characterization and identification of microplastics using Raman spectroscopy coupled with multivariate analysis

Naifu Jin et al.

Summary: The present study developed a new analytical method using Raman spectroscopy and multivariate analysis to comprehensively identify and quantify microplastics, achieving high accuracy through support vector machine classification. These findings demonstrate the importance and potential of Raman spectroscopy coupled with multivariate analysis for microplastic detection.

ANALYTICA CHIMICA ACTA (2022)

Article Environmental Sciences

Quantum cascade laser imaging (LDIR) and machine learning for the identification of environmentally exposed microplastics and polymers

Xin Tian et al.

Summary: This study presents a novel approach to identify weathered microplastics using a combination of supervised and unsupervised machine learning models. The accuracy of identification reached up to 89.7% using supervised models and additional subgroups of microplastics were detected using an unsupervised model. This approach can greatly accelerate the identification process and reduce the labeling efforts.

ENVIRONMENTAL RESEARCH (2022)

Article Environmental Sciences

Deep learning approach for automatic microplastics counting and classification

Javier Lorenzo-Navarro et al.

Summary: This paper presents an architecture based on deep learning networks for automatically counting and classifying microplastic particles, achieving remarkable results including a high Jaccard index value and accuracy.

SCIENCE OF THE TOTAL ENVIRONMENT (2021)

Article Environmental Sciences

A comparison of spectroscopic analysis methods for microplastics: Manual, semi-automated, and automated Fourier transform infrared and Raman techniques

Young Kyoung Song et al.

Summary: This study compared manual analysis, semi-automated method, and fully automated identification method, and found that the semi-automated analysis is more suitable for microplastic analysis, being less time-consuming and having higher detection rate.

MARINE POLLUTION BULLETIN (2021)

Article Chemistry, Analytical

Validated spreadsheet for the identification of PE, PET, PP and PS microplastics by micro-ATR-FTIR spectra with known uncertainty

Vanessa Morgado et al.

Summary: This study presents a methodology for reliably identifying the most common polymer types in aquatic sediments using micro-ATR-FTIR. Identifications with true and false result rates greater than 95% and lower than 5% are achieved. The analysis involves defining spectral requirements, selecting optimal assessed wavenumber range, and quantifying the match between particle and reference spectra.

TALANTA (2021)

Article Chemistry, Analytical

Microplastic Spectral Classification Needs an Open Source Community: Open Specy to the Rescue!

Win Cowger et al.

Summary: Open Specy is a free software solution for spectral classification, offering users the ability to view, process, identify, and share microplastic spectra. It stands out as the only open source software with a community library, and provides a range of tools for spectrum processing to build a diverse reference library for microplastics.

ANALYTICAL CHEMISTRY (2021)

Article Chemistry, Physical

Synthetic Image Rendering Solves Annotation Problem in Deep Learning Nanoparticle Segmentation

Leonid Mill et al.

Summary: This study presents an innovative method to generate realistic synthetic training data using rendering software for training deep neural networks, achieving comparable segmentation accuracy to manual annotations for toxicologically relevant metal-oxide nanoparticle ensembles. The research paves the way for the use of deep learning in automated, high-throughput particle detection in various imaging techniques, including the detection of micro- and nanoplastic particles in water and tissue samples.

SMALL METHODS (2021)

Article Computer Science, Interdisciplinary Applications

Using ATR-FTIR spectra and convolutional neural networks for characterizing mixed plastic waste

Shengli Jiang et al.

Summary: The study introduces a CNN framework for classifying different types of plastics in mixed plastic waste using experimental ATR-FTIR spectra, demonstrating significant improvements in classification accuracy.

COMPUTERS & CHEMICAL ENGINEERING (2021)

Article Biotechnology & Applied Microbiology

Microplastic constituent identification from admixtures by Fourier-transform infrared (FTIR) spectroscopy: The use of polyethylene terephthalate (PET), polyethylene (PE), polypropylene (PP), polyvinyl chloride (PVC) and nylon (NY) as the model constituents

Chihhao Fan et al.

Summary: The ubiquity of microplastics poses threats to the environment and ecology, making it crucial to identify their polymer constituents for pollution control and risk management. This study utilized Fourier-transform infrared spectroscopy to identify the various constituents of microplastics, proposing a procedure for microplastic identification.

ENVIRONMENTAL TECHNOLOGY & INNOVATION (2021)

Article Chemistry, Multidisciplinary

(Micro)plastics and the UN Sustainable Development Goals

Tony R. Walker

Summary: The implementation of the United Nations Sustainable Development Goals faces challenges from (micro)plastic pollution, mainly manifested in the insufficient monitoring indicators and the difficulty of monitoring.

CURRENT OPINION IN GREEN AND SUSTAINABLE CHEMISTRY (2021)

Article Biochemical Research Methods

SciPy 1.0: fundamental algorithms for scientific computing in Python

Pauli Virtanen et al.

NATURE METHODS (2020)

Review Instruments & Instrumentation

Critical Review of Processing and Classification Techniques for Images and Spectra in Microplastic Research

Win Cowger et al.

APPLIED SPECTROSCOPY (2020)

Review Multidisciplinary Sciences

Array programming with NumPy

Charles R. Harris et al.

NATURE (2020)

Article Multidisciplinary Sciences

Predicted growth in plastic waste exceeds efforts to mitigate plastic pollution

Stephanie B. Borrelle et al.

SCIENCE (2020)

Article Chemistry, Multidisciplinary

Spectral deep learning for prediction and prospective validation of functional groups

Jonathan A. Fine et al.

CHEMICAL SCIENCE (2020)

Article Biochemical Research Methods

Reference database design for the automated analysis of microplastic samples based on Fourier transform infrared (FTIR) spectroscopy

Sebastian Primpke et al.

ANALYTICAL AND BIOANALYTICAL CHEMISTRY (2018)

Article Computer Science, Hardware & Architecture

ImageNet Classification with Deep Convolutional Neural Networks

Alex Krizhevsky et al.

COMMUNICATIONS OF THE ACM (2017)

Article Environmental Sciences

Distribution and quantity of microplastic on sandy beaches along the northern coast of Taiwan

Alexander Kunz et al.

MARINE POLLUTION BULLETIN (2016)

Article Chemistry, Physical

In Situ FT-IR Spectroscopic Study of CO2 and CO Adsorption on Y2O3, ZrO2, and Yttria-Stabilized ZrO2

Eva-Maria Koeck et al.

JOURNAL OF PHYSICAL CHEMISTRY C (2013)

Article Computer Science, Artificial Intelligence

An introduction to ROC analysis

Tom Fawcett

PATTERN RECOGNITION LETTERS (2006)