Onderzoeksoutput

Welkom op het expertplatform!

Dit platform verschaft informatie en kennis omtrent de WL expertisedomeinen 'hydraulica en sediment', 'havens en waterwegen', 'waterbouwkundige constructies', 'waterbeheer' en 'kustbescherming' - gaande van WL medewerkers met hun expertise, het curriculum van deze instelling, tot publicaties, projecten, data (op termijn) en evenementen waarin het WL betrokken is.

Het WL onderschrijft het belang van "open access" voor de ontsluiting van haar onderzoeksresultaten. Lees er meer over in ons openaccessbeleid.

log in

• 
  People
• 
  Curriculum
• 
  Projects
• 
  Data sets
• 
  Publications
• 
  Events

[ meld een fout in dit record ]

mandje (0): toevoegen | toon

---

From microplastics to pixels: testing the robustness of two machine learning approaches for automated, Nile red-based marine microplastic identification Meyers, N.; De Witte, B.; Schmidt, N.; Herzke, D.; Fuda, J.-L.; Vanavermaete, D.; Janssen, C.R.; Everaert, G. (2024). From microplastics to pixels: testing the robustness of two machine learning approaches for automated, Nile red-based marine microplastic identification. Environm. Sc. & Poll. Res. 31: 61860–61875. https://dx.doi.org/10.1007/s11356-024-35289-0 In: Environmental Science and Pollution Research. Springer: Heidelberg; Berlin. ISSN 0944-1344; e-ISSN 1614-7499

---

Beschikbaar in	Auteurs
VLIZ: Non-open access 410134 [ aanvragen ] VLIZ: Open Marine Archive 410135 [ download pdf ] Reprint

---

Trefwoorden

Automation Fluorescence Machine learning Monitoring Pollution > Water pollution > Marine pollution Marien/Kust

Author keywords

Microplastics  · Fluorescence · Nile red · Weathered plastics

---

Auteurs		Top
Meyers, N. De Witte, B. Schmidt, N. Herzke, D.	Fuda, J.-L. Vanavermaete, D. Janssen, C.R. Everaert, G.

---

Abstract

Despite the urgent need for accurate and robust observations of microplastics in the marine environment to assess current and future environmental risks, existing procedures remain labour-intensive, especially for smaller-sized microplastics. In addition to this, microplastic analysis faces challenges due to environmental weathering, impacting the reliability of research relying on pristine plastics. This study addresses these knowledge gaps by testing the robustness of two automated analysis techniques which combine machine learning algorithms with fluorescent colouration of Nile red (NR)-stained particles. Heterogeneously shaped uncoloured microplastics of various polymers—polyethylene (PE), polyethylene terephthalate (PET), polypropylene (PP), polystyrene (PS), and polyvinyl chloride (PVC)—ranging from 100 to 1000 µm in size and weathered under semi-controlled surface and deep-sea conditions, were stained with NR and imaged using fluorescence stereomicroscopy. This study assessed and compared the accuracy of decision tree (DT) and random forest (RF) models in detecting and identifying these weathered plastics. Additionally, their analysis time and model complexity were evaluated, as well as the lower size limit (2–4 µm) and the interoperability of the approach. Decision tree and RF models were comparably accurate in detecting and identifying pristine plastic polymers (both > 90%). For the detection of weathered microplastics, both yielded sufficiently high accuracies (> 77%), although only RF models were reliable for polymer identification (> 70%), except for PET particles. The RF models showed an accuracy > 90% for particle predictions based on 12–30 pixels, which translated to microplastics sized < 10 µm. Although the RF classifier did not produce consistent results across different labs, the inherent flexibility of the method allows for its swift adaptation and optimisation, ensuring the possibility to fine-tune the method to specific research goals through customised datasets, thereby strengthening its robustness. The developed method is particularly relevant due to its ability to accurately analyse microplastics weathered under various marine conditions, as well as ecotoxicologically relevant microplastic sizes, making it highly applicable to real-world environmental samples.

---

Alle informatie in het Integrated Marine Information System (IMIS) valt onder het VLIZ Privacy beleid

Top | Auteurs

IMIS is ontwikkeld en wordt gehost door het VLIZ.