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

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. Highlights ► A machine learning algorithm was developed to determine the chemical nature of microplastics. ► This method allows a fast and reliable automated identification even when several thousand of FTIR spectra have to be studied.► This method is the first part of a software dedicated to the study of microplastics: POSEIDON.

Contributions of Fourier transform infrared spectroscopy in microplastic pollution research: A review

“…Moreover, training the classifier can increase the analysis speed substantially when dealing with large datasets of FTIR spectra. For example, automated identification methods were tested based on hierarchical cluster analysis (Primpke et al, 2018), shortwave infrared imaging (Schmidt et al, 2018), identification of the most relevant bands (Renner et al, 2017;Renner, Nellessen, et al, 2019), random decision forest method (Hufnagl et al, 2019), modified chemometric identification concept (Renner, Sauerbier, et al, 2019), machine learning method (Kedzierski et al, 2019), Python based lFTIR mapping (Renner et al, 2020) and Hybrid fusion method (Chabuka & Kalivas, 2020). The analysis of FTIR spectra is time-consuming as often it is needed to compare the spectra one by one with the reference spectra.…”

Microplastic Characterization by Infrared Spectroscopy

“…KNN is an approach for data classification that estimates how likely a data point is to be a member of one class or the other depending on what classes the data points nearest to it are in. Kedzierski et al (2019) carried out research to test KNN in the context of the studying of microplastics. Microplastic samples were collected from Mediterranean Sea waters.…”

Functional Group Identification for FTIR Spectra Using Image-Based Machine Learning Models

“…Progress towards machine learning (ML) methods for environmental pollutant analysis has been explored for specific, targeted applications. 9,[15][16][17] Generalizable functional group ML models would increase the utility of FTIR sample screening in environmental and other chemistry applications. 18,19 In this study, we investigate the implementation of convolutional neural networks (CNNs) 20 to identify functional groups present in FTIR spectra.…”