Communications of the ACM
Researchers Use ML to Speed Up Counting of Microplastics
Rather than using a tweezers to manually count microplastic samples under an optical microscope, University of Toronto researcher Bin Shi used scanning electron microscopes to segment images of microplastics and classify their shapes.
Credit: Bin Shi
Researchers at Canada's University of Toronto (U of T) have proposed a new machine learning method to accelerate the counting and classification of microplastics, while also boosting affordability and ease of use.
U of T's Elodie Passeport said she, Shuyao Tan, and Joshua Taylor "established a prediction model that employs a trained algorithm that can estimate microplastic counts from aggregate mass measurements."
Passeport explained the model "has guaranteed error-tracking properties with similar results to manual counting, but it's less costly and faster, allowing for the analysis of multiple samples from multiple points to estimate microplastic pollution."
The researchers found the method enables manual processing with just a fraction of collected samples, while algorithmically predicting the quantity of remaining samples without additional error or variance.
From University of Toronto News (Canada)
View Full Article
Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA
No entries found