Work

An Open-Source Computer-Vision-Based Method for Spherical Microplastic Settling Velocity Calculation

Year: 2025

Type: article

Abstract: Microplastics (particles ≤ 5 mm) are ubiquitous and persistent, posing threats to ecosystems and human health. Thus, the development of technologies for evaluating their dynamics is crucial. Settling velocity is a critical parameter for predicting the fate of microplastics in aquatic environments. Current methods for computing this metric are highly subjective and lack a standard. The goal of this research is to develop an objective, automated technique employing the technological advances in computer vision. In the laboratory, a camera recorded the trajectories of microplastics as they sank through a water column. The settling velocity of each microplastic was calculated using a YOLOv12n-based object detection model. The system was tested with three classes of spherical microplastics and three types of water. Ground truth settling times, recorded manually with a stopwatch, allowed for quantification of the system’s accuracy. When comparing the velocities calculated using the computer vision system to the stopwatch ground truth, the average error across all water types was 5.97% for the 3 mm microplastics, 7.14% for the 4 mm microplastics, and 6.15% for the 5 mm microplastics. This new method will enable the research community to predict microplastic distribution and transport patterns, as well as implement more timely strategies for mitigating pollution.

Source: Microplastics

DOI: 10.3390/microplastics4040075

Authors: Catherine L. Stacy, Md Abdul Baset Sarker, Abul B. M. Baki, Masudul H. Imtiaz

Institutions: Macalester College, Clarkson University

Language: English

Topic: Microplastics and Plastic Pollution

Subfield: Pollution

Field: Environmental Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,207

Funders: National Science Foundation, State University of New York, European Social Fund