We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
From microplastics to pixels: testing the robustness of two machine learning approaches for automated, Nile red-based marine microplastic identification
Summary
Two machine learning approaches using Nile red fluorescence staining and automated image analysis were tested for robustness on marine microplastics of multiple polymer types and weathering states, finding performance varied with particle heterogeneity and environmental aging.
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.
Sign in to start a discussion.
More Papers Like This
From microplastics to pixels: Testing the robustness of two machine learning approaches for automated, Nile red-based marine microplastic identification.
Researchers tested the robustness of two automated machine learning approaches combined with Nile red fluorescent staining for marine microplastic identification, specifically evaluating performance on environmentally weathered particles that challenge the reliability of methods developed using pristine laboratory plastics.
From microplastics to pixels: Testing the robustness of two machine learning approaches for automated, Nile red-based marine microplastic identification.
Researchers tested the robustness of decision tree and random forest machine learning classifiers combined with Nile red fluorescent staining for automated detection and identification of microplastic polymers weathered under semi-controlled surface water and deep-sea conditions for up to one year. They found both models achieved comparable accuracy above 90% for pristine plastics, but assessed how environmental weathering affected classification reliability, also evaluating analysis time, model complexity, size detection limits, and interoperability.
Machine learning enhanced machine vision system for micro-plastics particles classification
Researchers developed a machine learning-based classification system using fluorescence microscopy with Nile Red staining to identify and categorize microplastic types in environmental samples, aiming to provide a faster and more automated alternative to labor-intensive manual identification methods.
Towards reliable data: Validation of a machine learning-based approach for microplastics analysis in marine organisms using Nile red staining
This study validated a semi-automated machine learning workflow for microplastic analysis by spiking environmentally relevant particles into samples and recovering them, addressing the high cost and variability that limits comparability across MP studies. The approach aims to improve reliability and cost-effectiveness of routine microplastic analysis.
Microplastic detection and identification by Nile red staining: Towards a semi-automated, cost- and time-effective technique
Researchers developed a semi-automated, cost-effective method for microplastic detection using Nile red fluorescent staining, showing it can significantly reduce the time and expense of identifying microplastics compared to traditional spectroscopic approaches.