Training and evaluating machine learning algorithms for ocean microplastics classification through vibrational spectroscopy

Back, HdM, Vargas Junior, EC, Alarcon, OE and Pottmaier, D ORCID logoORCID: https://orcid.org/0000-0002-3766-2580, 2022. Training and evaluating machine learning algorithms for ocean microplastics classification through vibrational spectroscopy. Chemosphere, 287 (Part 1): 131903. ISSN 0045-6535

[thumbnail of 2181311_Pottmaier.pdf]
Preview
Text
2181311_Pottmaier.pdf - Post-print

Download (1MB) | Preview

Abstract

Microplastics are contaminants of emerging concern - not only environmental, but also to human health. Characterizing them is of fundamental importance to evaluate their potential impacts and target specific actions aiming to reduce potential harming effects. This study extends the exploration of machine learning classification algorithms applied to FTIR spectra of microplastics collected at sea. A comparison of successful classification models was made in order to evaluate prediction performance for 13 classes of polymers. A rigorous methodology was applied using a pipeline scheme to avoid bias in the training and selection phases. The application of an oversampling technique also contributed by compensating unbalanceness in the dataset. The log-loss was used as the minimization function target and to assess performance. In our analysis, Support Vector Machine Classifier provides a good relationship between simplicity and performance, for a fast and useful automatic characterization of microplastics.

Item Type: Journal article
Publication Title: Chemosphere
Creators: Back, H.M., Vargas Junior, E.C., Alarcon, O.E. and Pottmaier, D.
Publisher: Elsevier
Date: January 2022
Volume: 287
Number: Part 1
ISSN: 0045-6535
Identifiers:
Number
Type
10.1016/j.chemosphere.2021.131903
DOI
S0045653521023754
Publisher Item Identifier
2181311
Other
Divisions: Schools > School of Science and Technology
Record created by: Jonathan Gallacher
Date Added: 28 Aug 2024 11:14
Last Modified: 28 Aug 2024 11:14
URI: https://irep.ntu.ac.uk/id/eprint/52113

Actions (login required)

Edit View Edit View

Statistics

Views

Views per month over past year

Downloads

Downloads per month over past year