Big Data, Tiny Targets: An Exploratory Study in Machine Learning-enhanced Detection of Microplastic from Filters

TL;DR

This study explores using SEM imaging combined with machine learning, specifically YOLO models, to improve microplastic detection in environmental samples, highlighting current limitations and future research directions.

Contribution

It demonstrates the potential of ML-enhanced detection of microplastics using SEM images and identifies key challenges like data scarcity and model optimization.

Findings

YOLO models show varying effectiveness in microplastic detection.

Preprocessing optimization significantly impacts detection quality.

Limited labeled data remains a major challenge for reliable ML training.

Abstract

Microplastics (MPs) are ubiquitous pollutants with demonstrated potential to impact ecosystems and human health. Their microscopic size complicates detection, classification, and removal, especially in biological and environmental samples. While techniques like optical microscopy, Scanning Electron Microscopy (SEM), and Atomic Force Microscopy (AFM) provide a sound basis for detection, applying these approaches requires usually manual analysis and prevents efficient use in large screening studies. To this end, machine learning (ML) has emerged as a powerful tool in advancing microplastic detection. In this exploratory study, we investigate potential, limitations and future directions of advancing the detection and quantification of MP particles and fibres using a combination of SEM imaging and machine learning-based object detection. For simplicity, we focus on a filtration scenario where image backgrounds exhibit a symmetric and repetitive pattern. Our findings indicate differences in the quality of YOLO models for the given task and the relevance of optimizing preprocessing. At the same time, we identify open challenges, such as limited amounts of expert-labeled data necessary for reliable training of ML models.