A machine learning algorithm for high throughput identification of FTIR spectra: Application on microplastics collected in the Mediterranean Sea

Type Article
Date 2019-11
Language English
Author(s) Kedzierski Mikaël1, Falcou-Préfol Mathilde1, Kerros Marie Emmanuelle2, Henry Maryvonne3, Pedrotti Maria Luiza2, Bruzaud Stéphane1
Affiliation(s) 1 : Université Bretagne Sud, UMR CNRS 6027, IRDL, F-56100, Lorient, France
2 : Sorbonne Universités, UMR CNRS 7093, LOV, F-06230, Villefranche sur mer, France
3 : IFREMER, LER/PAC, F-83500, La Seine-sur-Mer, France
Source Chemosphere (0045-6535) (Elsevier BV), 2019-11 , Vol. 234 , P. 242-251
DOI 10.1016/j.chemosphere.2019.05.113
WOS© Times Cited 2
Note Multimedia component 1. - https://ars.els-cdn.com/content/image/1-s2.0-S0045653519310197-mmc1.zip
Keyword(s) Microplastic, Tara mediterranean campaign, FTIR spectra, Machine learning, k-nearest neighbor classification
Abstract

The development of methods to automatically determine the chemical nature of microplastics by FTIR-ATR spectra is an important challenge. A machine learning method, named k-nearest neighbors classification, has been applied on spectra of microplastics collected during Tara Expedition in the Mediterranean Sea (2014). To realize these tests, a learning database composed of 969 microplastic spectra has been created. Results show that the machine learning process is very efficient to identify spectra of classical polymers such as poly(ethylene), but also that the learning database must be enhanced with less common microplastic spectra. Finally, this method has been applied on more than 4000 spectra of unidentified microplastics. The verification protocol showed less than 10% difference in the results between the proposed automated method and a human expertise, 75% of which can be very easily corrected.

Full Text
File Pages Size Access
Author's final draft 29 1 MB Open access
10 1 MB Access on demand
Top of the page

How to cite 

Kedzierski Mikaël, Falcou-Préfol Mathilde, Kerros Marie Emmanuelle, Henry Maryvonne, Pedrotti Maria Luiza, Bruzaud Stéphane (2019). A machine learning algorithm for high throughput identification of FTIR spectra: Application on microplastics collected in the Mediterranean Sea. Chemosphere, 234, 242-251. Publisher's official version : https://doi.org/10.1016/j.chemosphere.2019.05.113 , Open Access version : https://archimer.ifremer.fr/doc/00501/61247/