Aarhus University Seal / Aarhus Universitets segl

Classification and Quantification of Microplastics (<100 μm) Using a Focal Plane Array–Fourier Transform Infrared Imaging System and Machine Learning

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Standard

Classification and Quantification of Microplastics (<100 μm) Using a Focal Plane Array–Fourier Transform Infrared Imaging System and Machine Learning. / da Silva, Vitor Hugo; Murphy, Fionn; Amigo, José et al.

In: Analytical Chemistry, Vol. 92, No. 20, 10.2020, p. 13724-13733.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Harvard

APA

CBE

MLA

Vancouver

Author

Bibtex

@article{2be10436928e40f3bdee4212da40d1c7,
title = "Classification and Quantification of Microplastics (<100 μm) Using a Focal Plane Array–Fourier Transform Infrared Imaging System and Machine Learning",
abstract = "Microplastics are defined as microscopic plastic particles in the range from few micrometers and up to 5 mm. These small particles are classified as primary microplastics when they are manufactured in this size range, whereas secondary microplastics arise from the fragmentation of larger objects. Microplastics are widespread emerging pollutants, and investigations are underway to determine potential harmfulness to biota and human health. However, progress is hindered by the lack of suitable analytical methods for rapid, routine, and unbiased measurements. This work aims to develop an automated analytical method for the characterization of small microplastics (<100 μm) using micro-Fourier transform infrared (μ-FTIR) hyperspectral imaging and machine learning tools. Partial least squares discriminant analysis (PLS-DA) and soft independent modeling of class analogy (SIMCA) models were evaluated, applying different data preprocessing strategies for classification of nine of the most common polymers produced worldwide. The hyperspectral images were also analyzed to quantify particle abundance and size automatically. PLS-DA presented a better analytical performance in comparison with SIMCA models with higher sensitivity, sensibility, and lower misclassification error. PLS-DA was less sensitive to edge effects on spectra and poorly focused regions of particles. The approach was tested on a seabed sediment sample (Roskilde Fjord, Denmark) to demonstrate the method efficiency. The proposed method offers an efficient automated approach for microplastic polymer characterization, abundance numeration, and size distribution with substantial benefits for method standardization.",
author = "{da Silva}, {Vitor Hugo} and Fionn Murphy and Jos{\'e} Amigo and Colin Stedmon and Jakob Strand",
year = "2020",
month = oct,
doi = "10.1021/acs.analchem.0c01324",
language = "English",
volume = "92",
pages = "13724--13733",
journal = "Analytical Chemistry",
issn = "0003-2700",
publisher = "AMER CHEMICAL SOC",
number = "20",

}

RIS

TY - JOUR

T1 - Classification and Quantification of Microplastics (<100 μm) Using a Focal Plane Array–Fourier Transform Infrared Imaging System and Machine Learning

AU - da Silva, Vitor Hugo

AU - Murphy, Fionn

AU - Amigo, José

AU - Stedmon, Colin

AU - Strand, Jakob

PY - 2020/10

Y1 - 2020/10

N2 - Microplastics are defined as microscopic plastic particles in the range from few micrometers and up to 5 mm. These small particles are classified as primary microplastics when they are manufactured in this size range, whereas secondary microplastics arise from the fragmentation of larger objects. Microplastics are widespread emerging pollutants, and investigations are underway to determine potential harmfulness to biota and human health. However, progress is hindered by the lack of suitable analytical methods for rapid, routine, and unbiased measurements. This work aims to develop an automated analytical method for the characterization of small microplastics (<100 μm) using micro-Fourier transform infrared (μ-FTIR) hyperspectral imaging and machine learning tools. Partial least squares discriminant analysis (PLS-DA) and soft independent modeling of class analogy (SIMCA) models were evaluated, applying different data preprocessing strategies for classification of nine of the most common polymers produced worldwide. The hyperspectral images were also analyzed to quantify particle abundance and size automatically. PLS-DA presented a better analytical performance in comparison with SIMCA models with higher sensitivity, sensibility, and lower misclassification error. PLS-DA was less sensitive to edge effects on spectra and poorly focused regions of particles. The approach was tested on a seabed sediment sample (Roskilde Fjord, Denmark) to demonstrate the method efficiency. The proposed method offers an efficient automated approach for microplastic polymer characterization, abundance numeration, and size distribution with substantial benefits for method standardization.

AB - Microplastics are defined as microscopic plastic particles in the range from few micrometers and up to 5 mm. These small particles are classified as primary microplastics when they are manufactured in this size range, whereas secondary microplastics arise from the fragmentation of larger objects. Microplastics are widespread emerging pollutants, and investigations are underway to determine potential harmfulness to biota and human health. However, progress is hindered by the lack of suitable analytical methods for rapid, routine, and unbiased measurements. This work aims to develop an automated analytical method for the characterization of small microplastics (<100 μm) using micro-Fourier transform infrared (μ-FTIR) hyperspectral imaging and machine learning tools. Partial least squares discriminant analysis (PLS-DA) and soft independent modeling of class analogy (SIMCA) models were evaluated, applying different data preprocessing strategies for classification of nine of the most common polymers produced worldwide. The hyperspectral images were also analyzed to quantify particle abundance and size automatically. PLS-DA presented a better analytical performance in comparison with SIMCA models with higher sensitivity, sensibility, and lower misclassification error. PLS-DA was less sensitive to edge effects on spectra and poorly focused regions of particles. The approach was tested on a seabed sediment sample (Roskilde Fjord, Denmark) to demonstrate the method efficiency. The proposed method offers an efficient automated approach for microplastic polymer characterization, abundance numeration, and size distribution with substantial benefits for method standardization.

U2 - 10.1021/acs.analchem.0c01324

DO - 10.1021/acs.analchem.0c01324

M3 - Journal article

C2 - 32942858

VL - 92

SP - 13724

EP - 13733

JO - Analytical Chemistry

JF - Analytical Chemistry

SN - 0003-2700

IS - 20

ER -