Accurate detection of low concentrations of microplastics in soils via short-wave infrared hyperspectral imaging

This study evaluated the effectiveness of coupling machine learning algorithms with short-wave infrared hyperspectral imaging in detecting two types of microplastics - polyamide and polyethylene - with the maximum particle sizes of 50 and 300 ​μm, respectively, across three concentration ranges (0.0...

Full description

Saved in:
Bibliographic Details
Main Authors: Huan Chen, Taesung Shin, Bosoon Park, Kyoung Ro, Changyoon Jeong, Hwang-Ju Jeon, Pei-Lin Tan
Format: Article
Language:English
Published: Elsevier 2025-07-01
Series:Soil & Environmental Health
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2949919425000305
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849318432645840896
author Huan Chen
Taesung Shin
Bosoon Park
Kyoung Ro
Changyoon Jeong
Hwang-Ju Jeon
Pei-Lin Tan
author_facet Huan Chen
Taesung Shin
Bosoon Park
Kyoung Ro
Changyoon Jeong
Hwang-Ju Jeon
Pei-Lin Tan
author_sort Huan Chen
collection DOAJ
description This study evaluated the effectiveness of coupling machine learning algorithms with short-wave infrared hyperspectral imaging in detecting two types of microplastics - polyamide and polyethylene - with the maximum particle sizes of 50 and 300 ​μm, respectively, across three concentration ranges (0.01–0.10, 0.10–1.0, and 1.0–12 ​%) in soils. Using indium gallium arsenide (InGaAs; 800–1600 ​nm) and mercury cadmium telluride (MCT; 1000–2500 ​nm) sensors, we applied logistic regression and support vector machines by employing both linear and nonlinear kernels to analyze spectral features extracted via principal component analysis and partial least squares. The results demonstrated that the overall accuracy for detecting 0.01–12% microplastics was 93.8 ​± ​1.47% using the MCT sensor, which was higher than 68.8 ​± ​3.76 ​% using the InGaAs sensor. Both sensors showed high accuracy (>94 ​%) when detecting high levels at 1.0–12%) of microplastics in soil. But these accuracies greatly declined as the spiked microplastics concentrations decreased from 1.0–12 to 0.10–1.0% and further to 0.01–0.10%. Moreover, this decline was more pronounced for the InGaAs sensor compared to the MCT sensor and for sub-wavelength spans compared to the full wavelength span under each sensor. The MCT sensor consistently outperformed the InGaAs sensor across all three concentration ranges, potentially due to its extended coverage of 1600–2500 ​nm and high sensitivity of the detector. Our study highlights the feasibility of the MCT hyperspectral imaging system for rapid and effective detection of microplastics in soils non-invasively at concentrations as low as 0.01%.
format Article
id doaj-art-dbf613608c9e4ee9b714ef84e115d868
institution Kabale University
issn 2949-9194
language English
publishDate 2025-07-01
publisher Elsevier
record_format Article
series Soil & Environmental Health
spelling doaj-art-dbf613608c9e4ee9b714ef84e115d8682025-08-20T03:50:49ZengElsevierSoil & Environmental Health2949-91942025-07-013310015710.1016/j.seh.2025.100157Accurate detection of low concentrations of microplastics in soils via short-wave infrared hyperspectral imagingHuan Chen0Taesung Shin1Bosoon Park2Kyoung Ro3Changyoon Jeong4Hwang-Ju Jeon5Pei-Lin Tan6Department of Environmental Engineering and Earth Sciences, Clemson University, Clemson, SC, 29634, USAUSDA Agricultural Research Service, U.S. National Poultry Research Center, Athens, GA, 30605, USAUSDA Agricultural Research Service, U.S. National Poultry Research Center, Athens, GA, 30605, USA; Corresponding author.USDA Agricultural Research Service, Coastal Plains Soil, Water & Plant Research Center, Florence, SC, 29501, USARed River Research Station, Louisiana State University Agricultural Center, Bossier City, LA, 71112, USARed River Research Station, Louisiana State University Agricultural Center, Bossier City, LA, 71112, USADepartment of Forestry and Environmental Conservation, Clemson University, South Carolina, 29634, USAThis study evaluated the effectiveness of coupling machine learning algorithms with short-wave infrared hyperspectral imaging in detecting two types of microplastics - polyamide and polyethylene - with the maximum particle sizes of 50 and 300 ​μm, respectively, across three concentration ranges (0.01–0.10, 0.10–1.0, and 1.0–12 ​%) in soils. Using indium gallium arsenide (InGaAs; 800–1600 ​nm) and mercury cadmium telluride (MCT; 1000–2500 ​nm) sensors, we applied logistic regression and support vector machines by employing both linear and nonlinear kernels to analyze spectral features extracted via principal component analysis and partial least squares. The results demonstrated that the overall accuracy for detecting 0.01–12% microplastics was 93.8 ​± ​1.47% using the MCT sensor, which was higher than 68.8 ​± ​3.76 ​% using the InGaAs sensor. Both sensors showed high accuracy (>94 ​%) when detecting high levels at 1.0–12%) of microplastics in soil. But these accuracies greatly declined as the spiked microplastics concentrations decreased from 1.0–12 to 0.10–1.0% and further to 0.01–0.10%. Moreover, this decline was more pronounced for the InGaAs sensor compared to the MCT sensor and for sub-wavelength spans compared to the full wavelength span under each sensor. The MCT sensor consistently outperformed the InGaAs sensor across all three concentration ranges, potentially due to its extended coverage of 1600–2500 ​nm and high sensitivity of the detector. Our study highlights the feasibility of the MCT hyperspectral imaging system for rapid and effective detection of microplastics in soils non-invasively at concentrations as low as 0.01%.http://www.sciencedirect.com/science/article/pii/S2949919425000305PolyamidePolyethyleneMachine learningPartial least squaresPrincipal conponent analysisLinear and nonliearn kernels
spellingShingle Huan Chen
Taesung Shin
Bosoon Park
Kyoung Ro
Changyoon Jeong
Hwang-Ju Jeon
Pei-Lin Tan
Accurate detection of low concentrations of microplastics in soils via short-wave infrared hyperspectral imaging
Soil & Environmental Health
Polyamide
Polyethylene
Machine learning
Partial least squares
Principal conponent analysis
Linear and nonliearn kernels
title Accurate detection of low concentrations of microplastics in soils via short-wave infrared hyperspectral imaging
title_full Accurate detection of low concentrations of microplastics in soils via short-wave infrared hyperspectral imaging
title_fullStr Accurate detection of low concentrations of microplastics in soils via short-wave infrared hyperspectral imaging
title_full_unstemmed Accurate detection of low concentrations of microplastics in soils via short-wave infrared hyperspectral imaging
title_short Accurate detection of low concentrations of microplastics in soils via short-wave infrared hyperspectral imaging
title_sort accurate detection of low concentrations of microplastics in soils via short wave infrared hyperspectral imaging
topic Polyamide
Polyethylene
Machine learning
Partial least squares
Principal conponent analysis
Linear and nonliearn kernels
url http://www.sciencedirect.com/science/article/pii/S2949919425000305
work_keys_str_mv AT huanchen accuratedetectionoflowconcentrationsofmicroplasticsinsoilsviashortwaveinfraredhyperspectralimaging
AT taesungshin accuratedetectionoflowconcentrationsofmicroplasticsinsoilsviashortwaveinfraredhyperspectralimaging
AT bosoonpark accuratedetectionoflowconcentrationsofmicroplasticsinsoilsviashortwaveinfraredhyperspectralimaging
AT kyoungro accuratedetectionoflowconcentrationsofmicroplasticsinsoilsviashortwaveinfraredhyperspectralimaging
AT changyoonjeong accuratedetectionoflowconcentrationsofmicroplasticsinsoilsviashortwaveinfraredhyperspectralimaging
AT hwangjujeon accuratedetectionoflowconcentrationsofmicroplasticsinsoilsviashortwaveinfraredhyperspectralimaging
AT peilintan accuratedetectionoflowconcentrationsofmicroplasticsinsoilsviashortwaveinfraredhyperspectralimaging