Classification of Microplastic Particles in Water using Polarized Light Scattering and Machine Learning Methods

TL;DR

This study develops a polarization-based optical and deep learning framework for accurately classifying microplastic particles in water, overcoming limitations of traditional methods and revealing internal structural features.

Contribution

It introduces a novel backscattering polarimetry approach combined with deep learning for microplastic classification, emphasizing internal polarization textures over surface features.

Findings

Achieved 83% classification accuracy on microplastic types.

Demonstrated internal polarization textures are key for classification.

Outlier removal improves model stability and generalization.

Abstract

The detection and classification of microplastics in water remain a significant challenge due to their diverse properties and the limitations of traditional optical methods. Standard spectroscopic techniques often suffer from the strong infrared absorption of water, while many emerging optical approaches rely on transmission geometries that require sample transparency. This study presents a systematic classification framework utilizing 120 degree backscattering reflection polarimetry and deep learning to identify common polymers (HDPE, LDPE, and PP) directly in water. This backscattering-based approach is specifically designed to analyze opaque, irregularly shaped particles that lack distinguishable surface features under standard illumination. To ensure high-fidelity data, we introduce a feedback review loop to identify and remove outliers, which significantly stabilizes model training and improves generalization. This framework is validated on a dataset of 600 individually imaged microplastic fragments spanning three polymer types. Our results evaluate the distinct contributions of the Angle of Linear Polarization and the Degree of Linear Polarization to the classification process. By implementing a late fusion architecture to combine these signals, we achieve an average test accuracy of 83 percent. Finally, a systematic feature hierarchy analysis reveals that the convolutional neural network relies on internal polarization textures associated with the particle's microstructure, rather than on macro-contours, with classification accuracy declining by over 40 percent when internal structure is removed. This demonstrates that the system extracts polarization-dependent internal structural information that is inaccessible to conventional intensity-only imaging methods.