EUVIMEDObjevte EUVIMED
Crossref

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

Yanlong Liu, Wenli Yao, Fenghui Qin, Lei Zhou iD, Yian Zheng iD

Environmental Science & Technology · 2023-04-25 · 57 (16) · 6656-6663

DOI: 10.1021/acs.est.2c08952 ↗

At a glance

Journal article in Environmental Science & Technology, published online on 2023-04-13. Written by Yanlong Liu and 4 co-authors. Institution: Gansu Key Laboratory for Environmental Pollution Prediction and Control, College of Earth and Environmental Sciences, Lanzhou University, Lanzhou, Ga…. Major MEDLINE topics: Plastics, Machine Learning. Cited 93 times so far (Crossref); 47 references. Funded by: National Natural Science Foundation of China, Natural Science Foundation of Gansu Province.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Microplastics (MPs) are currently recognized as emerging pollutants; their identification and classification are therefore essential during their monitoring and management. In contrast to most studies based on small datasets and library searches, this study developed and compared four machine learning-based classifiers and two large-scale blended plastic datasets, where a 1D convolutional neural network (CNN), decision tree, and random forest (RF) were fed with raw spectral data from Fourier transform infrared spectroscopy, while a 2D CNN used the corresponding spectral images as the input. With an overall accuracy of 96.43% on a small dataset and 97.44% on a large dataset, the 1D CNN outperformed other models. The 1D CNN was the best at predicting environment samples, while the RF was the most robust with less spectral data. Overall, RF and 2D CNNs might be evaluated for plastic identification with fewer spectral data; however, 1D CNNs were thought to be the most effective with sufficient spectral data. Accordingly, an open-source MP spectroscopic analysis tool was developed to facilitate a quick and accurate analysis of existing MP samples.

Subjects

MeSH terms (MEDLINE)

PlasticsMachine LearningSpectroscopy, Fourier Transform InfraredNeural Networks, ComputerMicroplastics

Author keywords

FT-IRclassificationmachine learningmicroplasticneural network

Substances

PlasticsMicroplastics

Authors and institutions

  • Gansu Key Laboratory for Environmental Pollution Prediction and Control, College of Earth and Environmental Sciences, Lanzhou University, Lanzhou, Gansu 730000, China.
  • College of Chemistry and Chemical Engineering, Lanzhou University, Lanzhou, Gansu 730000, China.

ORCID profiles: Lei Zhou, Yian Zheng

Funding

  • National Natural Science Foundation of China
  • Natural Science Foundation of Gansu Province

Cite

APA

Liu, Y., Yao, W., Qin, F., Zhou, L., & Zheng, Y. (2023). Spectral Classification of Large-Scale Blended (Micro)Plastics Using FT-IR Raw Spectra and Image-Based Machine Learning. Environmental Science & Technology, 57(16), 6656-6663. https://doi.org/10.1021/acs.est.2c08952

Vancouver

Liu Y, Yao W, Qin F, Zhou L, Zheng Y. Spectral Classification of Large-Scale Blended (Micro)Plastics Using FT-IR Raw Spectra and Image-Based Machine Learning. Environmental Science & Technology. 2023;57(16):6656-6663. doi:10.1021/acs.est.2c08952

BibTeX
@article{Liu2023,
  author = {Liu, Yanlong and Yao, Wenli and Qin, Fenghui and Zhou, Lei and Zheng, Yian},
  title = {Spectral Classification of Large-Scale Blended (Micro)Plastics Using FT-IR Raw Spectra and Image-Based Machine Learning},
  journal = {Environmental Science & Technology},
  year = {2023},
  volume = {57},
  number = {16},
  pages = {6656--6663},
  doi = {10.1021/acs.est.2c08952}
}
Start for free →