Mie scattering and microparticle-based characterization of heavy metal ions and classification by statistical inference methods

Katherine E. Klug, Christian M. Jennings, Nicholas Lytal, Lingling An, Jeong-Yeol Yoon

Research output: Contribution to journalArticle

Abstract

A straightforward method for classifying heavy metal ions in water is proposed using statistical classification and clustering techniques from non-specific microparticle scattering data. A set of carboxylated polystyrene microparticles of sizes 0.91, 0.75 and 0.40 mm was mixed with the solutions of nine heavy metal ions and two control cations, and scattering measurements were collected at two angles optimized for scattering from non-aggregated and aggregated particles. Classification of these observations was conducted and compared among several machine learning techniques, including linear discriminant analysis, support vector machine analysis, K-means clustering and K-medians clustering. This study found the highest classification accuracy using the linear discriminant and support vector machine analysis, each reporting high classification rates for heavy metal ions with respect to the model. This may be attributed to moderate correlation between detection angle and particle size. These classification models provide reasonable discrimination between most ion species, with the highest distinction seen for Pb(II), Cd(II), Ni(II) and Co(II), followed by Fe(II) and Fe(III), potentially due to its known sorption with carboxyl groups. The support vector machine analysis was also applied to three different mixture solutions representing leaching from pipes and mine tailings, and showed good correlation with single-species data, specifically with Pb(II) and Ni(II). With more expansive training data and further processing, this method shows promise for low-cost and portable heavy metal identification and sensing.

Original languageEnglish (US)
Article number190001
JournalRoyal Society Open Science
Volume6
Issue number5
DOIs
StatePublished - May 1 2019

Fingerprint

scattering
heavy metal
ion
discriminant analysis
tailings
pipe
sorption
cation
leaching
particle size
method
cost
support vector machine
analysis
water

Keywords

  • Heavy metal
  • Light scattering
  • Polystyrene
  • Statistical classification
  • Support vector machines

ASJC Scopus subject areas

  • General

Cite this

Mie scattering and microparticle-based characterization of heavy metal ions and classification by statistical inference methods. / Klug, Katherine E.; Jennings, Christian M.; Lytal, Nicholas; An, Lingling; Yoon, Jeong-Yeol.

In: Royal Society Open Science, Vol. 6, No. 5, 190001, 01.05.2019.

Research output: Contribution to journalArticle

@article{993adc3277714c5fa9274f0b45c37d0e,
title = "Mie scattering and microparticle-based characterization of heavy metal ions and classification by statistical inference methods",
abstract = "A straightforward method for classifying heavy metal ions in water is proposed using statistical classification and clustering techniques from non-specific microparticle scattering data. A set of carboxylated polystyrene microparticles of sizes 0.91, 0.75 and 0.40 mm was mixed with the solutions of nine heavy metal ions and two control cations, and scattering measurements were collected at two angles optimized for scattering from non-aggregated and aggregated particles. Classification of these observations was conducted and compared among several machine learning techniques, including linear discriminant analysis, support vector machine analysis, K-means clustering and K-medians clustering. This study found the highest classification accuracy using the linear discriminant and support vector machine analysis, each reporting high classification rates for heavy metal ions with respect to the model. This may be attributed to moderate correlation between detection angle and particle size. These classification models provide reasonable discrimination between most ion species, with the highest distinction seen for Pb(II), Cd(II), Ni(II) and Co(II), followed by Fe(II) and Fe(III), potentially due to its known sorption with carboxyl groups. The support vector machine analysis was also applied to three different mixture solutions representing leaching from pipes and mine tailings, and showed good correlation with single-species data, specifically with Pb(II) and Ni(II). With more expansive training data and further processing, this method shows promise for low-cost and portable heavy metal identification and sensing.",
keywords = "Heavy metal, Light scattering, Polystyrene, Statistical classification, Support vector machines",
author = "Klug, {Katherine E.} and Jennings, {Christian M.} and Nicholas Lytal and Lingling An and Jeong-Yeol Yoon",
year = "2019",
month = "5",
day = "1",
doi = "10.1098/rsos.190001",
language = "English (US)",
volume = "6",
journal = "Royal Society Open Science",
issn = "2054-5703",
publisher = "The Royal Society",
number = "5",

}

TY - JOUR

T1 - Mie scattering and microparticle-based characterization of heavy metal ions and classification by statistical inference methods

AU - Klug, Katherine E.

AU - Jennings, Christian M.

AU - Lytal, Nicholas

AU - An, Lingling

AU - Yoon, Jeong-Yeol

PY - 2019/5/1

Y1 - 2019/5/1

N2 - A straightforward method for classifying heavy metal ions in water is proposed using statistical classification and clustering techniques from non-specific microparticle scattering data. A set of carboxylated polystyrene microparticles of sizes 0.91, 0.75 and 0.40 mm was mixed with the solutions of nine heavy metal ions and two control cations, and scattering measurements were collected at two angles optimized for scattering from non-aggregated and aggregated particles. Classification of these observations was conducted and compared among several machine learning techniques, including linear discriminant analysis, support vector machine analysis, K-means clustering and K-medians clustering. This study found the highest classification accuracy using the linear discriminant and support vector machine analysis, each reporting high classification rates for heavy metal ions with respect to the model. This may be attributed to moderate correlation between detection angle and particle size. These classification models provide reasonable discrimination between most ion species, with the highest distinction seen for Pb(II), Cd(II), Ni(II) and Co(II), followed by Fe(II) and Fe(III), potentially due to its known sorption with carboxyl groups. The support vector machine analysis was also applied to three different mixture solutions representing leaching from pipes and mine tailings, and showed good correlation with single-species data, specifically with Pb(II) and Ni(II). With more expansive training data and further processing, this method shows promise for low-cost and portable heavy metal identification and sensing.

AB - A straightforward method for classifying heavy metal ions in water is proposed using statistical classification and clustering techniques from non-specific microparticle scattering data. A set of carboxylated polystyrene microparticles of sizes 0.91, 0.75 and 0.40 mm was mixed with the solutions of nine heavy metal ions and two control cations, and scattering measurements were collected at two angles optimized for scattering from non-aggregated and aggregated particles. Classification of these observations was conducted and compared among several machine learning techniques, including linear discriminant analysis, support vector machine analysis, K-means clustering and K-medians clustering. This study found the highest classification accuracy using the linear discriminant and support vector machine analysis, each reporting high classification rates for heavy metal ions with respect to the model. This may be attributed to moderate correlation between detection angle and particle size. These classification models provide reasonable discrimination between most ion species, with the highest distinction seen for Pb(II), Cd(II), Ni(II) and Co(II), followed by Fe(II) and Fe(III), potentially due to its known sorption with carboxyl groups. The support vector machine analysis was also applied to three different mixture solutions representing leaching from pipes and mine tailings, and showed good correlation with single-species data, specifically with Pb(II) and Ni(II). With more expansive training data and further processing, this method shows promise for low-cost and portable heavy metal identification and sensing.

KW - Heavy metal

KW - Light scattering

KW - Polystyrene

KW - Statistical classification

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=85066951159&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066951159&partnerID=8YFLogxK

U2 - 10.1098/rsos.190001

DO - 10.1098/rsos.190001

M3 - Article

AN - SCOPUS:85066951159

VL - 6

JO - Royal Society Open Science

JF - Royal Society Open Science

SN - 2054-5703

IS - 5

M1 - 190001

ER -