Automated machine-learning-driven analysis of microplastics by TGA-FTIR for enhanced identification and quantification

From National Research Council Canada

Download	View final version: Automated machine-learning-driven analysis of microplastics by TGA-FTIR for enhanced identification and quantification (PDF, 3.6 MiB) View supplementary information: Automated machine-learning-driven analysis of microplastics by TGA-FTIR for enhanced identification and quantification (PDF, 583 KiB)
DOI	Resolve DOI: https://doi.org/10.1021/acs.analchem.4c06775
Author	Search for: Prezgot, Daniel¹ORCID identifier: https://orcid.org/0000-0001-6498-4422; Search for: Chen, Maohui¹; Search for: Leng, Yingshu¹ORCID identifier: https://orcid.org/0000-0002-7048-494X; Search for: Gaburici, Liliana²; Search for: Zou, Shan¹ORCID identifier: https://orcid.org/0000-0002-2480-6821
Affiliation	National Research Council of Canada. Metrology Research Centre National Research Council of Canada. Quantum and Nanotechnologies
Funder	Search for: National Research Council of Canada; Search for: Government of Canada
Format	Text, Article
Subject	Fourier transform infrared spectroscopy; mathematical methods; mixtures; plastics; plymers
Abstract	Microplastics persist as ubiquitous environmental contaminants, and efficient methods to quantify and identify their presence are essential for assessing their environmental and health impacts. Common identification approaches typically fall under either vibrational spectroscopy or thermoanalytical techniques with thermogravimetric analysis (TGA) coupled with Fourier transform infrared (FTIR) spectroscopy bridging the intersection. Despite its potential, TGA-FTIR remains relatively underutilized for microplastic analysis, even though each thermogram is associated with approximately 200 FTIR spectra that can be rapidly assessed with targeted automated data analysis. This work explores the development of data analysis routines specialized in identifying plastic components from TGA-FTIR. A dedicated spectral library and a matching algorithm were created to identify polymers from their gas-phase FTIR spectra. The approach was further enhanced by utilizing machine learning (ML) classification techniques, including k-nearest neighbor, random forest, support vector classifier, and multilayer perceptron. The performance of these classifiers for complex data sets was evaluated using synthetic data sets generated from the spectral library. ML techniques offered precise and unambiguous identification compared with a custom spectral matching algorithm. By correlating polymer identities with mass loss in the thermogram, this approach combines qualitative insights with semiquantitative analysis, enabling a streamlined assessment of plastic content in samples.
Publication date	2025-04-16
Publisher	American Chemical Society
Licence	Creative Commons, Attribution 4.0 International (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/
In	Analytical Chemistry (16 April 2025): 1–8.
Related data	Prezgot, Daniel, Maohui Chen, Yinshu Leng, Liliana Gaburici, and Shan Zou. ‘Automated Machine-Learning Driven Analysis of Microplastics by TGA-FTIR for Enhanced Identification and Quantification’. National Research Council of Canada, 11 February 2025. https://doi.org/10.4224/40003458.
Language	English
Peer reviewed	Yes
Export citation	Export as RIS
Report a correction	Report a correction (opens in a new tab)
Record identifier	81002e37-fc57-4565-b703-91406acdd365
Record created	2025-04-17
Record modified	2025-04-22

Date modified:: 2025-04-25