Language selection

Government of Canada / Gouvernement du Canada

Search

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

From National Research Council Canada

Download
FileFormatSize
ZIP120.8 MiB
ZIP46 KiB
  • TGA-FTIR library datasets.zip contains combined TGA-FTIR data for all polymers included in the reference library, including the associated temperature, TG, DTG, Gram-Schmidt (integrated absorbance), and absorbance spectra.
  • TGA-FTIR Python notebooks.zip contains Python scripts in the form of Jupyter notebooks for the handling of data, creation of spectral libraries, training of machine learning models and identification and quantification by machine learning or custom spectral matching.
DOIResolve DOI: https://doi.org/10.4224/40003458
AuthorSearch for: 1ORCID identifier: https://orcid.org/0000-0001-6498-4422; Search for: 1; Search for: 1ORCID identifier: https://orcid.org/0000-0002-7048-494X; Search for: 2; Search for: 1ORCID identifier: https://orcid.org/0000-0002-2480-6821
Affiliation
  1. National Research Council of Canada. Metrology Research Centre
  2. National Research Council of Canada. Quantum and Nanotechnologies
FormatText, Dataset
Abstract
Microplastics persist as a ubiquitous environmental contaminant, 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 spectroscopy (FTIR) 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 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 perceptrons. The performance of these classifiers for complex datasets was evaluated using synthetic datasets generated from the spectral library. ML techniques offered precise and unambiguous identification compared to a custom spectral matching algorithm. By correlating polymer identities with mass-loss in the thermogram, this approach combines qualitative insights with semi-quantitative analysis, enabling a streamlined assessment of plastic content in samples.
Publication date
Date created2024
PublisherNational Research Council of Canada
Licence
Related publication
  • Prezgot, Daniel, Maohui Chen, Yingshu Leng, Liliana Gaburici, and Shan Zou. ‘Automated Machine-Learning-Driven Analysis of Microplastics by TGA-FTIR for Enhanced Identification and Quantification’. Analytical Chemistry, 16 April 2025. https://doi.org/10.1021/acs.analchem.4c06775.
LanguageEnglish
Export citationExport as RIS
CollectionNRC Research Data
Record identifier6fef0400-f3af-4f25-9fda-739c269ab5df
Record created2025-02-10
Record modified2025-04-28
Date modified: