FN Archimer Export Format
PT J
TI A machine learning algorithm for high throughput identification of FTIR spectra: Application on microplastics collected in the Mediterranean Sea
BT 
AF Kedzierski, Mikaël
   Falcou-Préfol, Mathilde
   Kerros, Marie Emmanuelle
   Henry, Maryvonne
   Pedrotti, Maria Luiza
   Bruzaud, Stéphane
AS 1:1;2:1;3:2;4:3;5:2;6:1;
FF 1:;2:;3:;4:PDG-ODE-LITTORAL-LERPAC;5:;6:;
C1 Université Bretagne Sud, UMR CNRS 6027, IRDL, F-56100, Lorient, France
   Sorbonne Universités, UMR CNRS 7093, LOV, F-06230, Villefranche sur mer, France
   IFREMER, LER/PAC, F-83500, La Seine-sur-Mer, France
C2 UBS, FRANCE
   UNIV PARIS 06, FRANCE
   IFREMER, FRANCE
SI TOULON
SE PDG-ODE-LITTORAL-LERPAC
IN WOS Ifremer UPR
   copubli-france
   copubli-univ-france
IF 5.778
TC 81
UR https://archimer.ifremer.fr/doc/00501/61247/64825.pdf
LA English
DT Article
DE ;Microplastic;Tara mediterranean campaign;FTIR spectra;Machine learning;k-nearest neighbor classification
AB 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. 
PY 2019
PD NOV
SO Chemosphere
SN 0045-6535
PU Elsevier BV
VL 234
UT 000488136200025
BP 242
EP 251
DI 10.1016/j.chemosphere.2019.05.113
ID 61247
ER

EF