Explainable deep-learning detection of microplastic fibers via polarization-resolved holographic microscopy

TL;DR

This paper presents an explainable deep-learning method using polarization-resolved holographic microscopy for accurate microplastic fiber identification, revealing optical fingerprints and outperforming traditional classifiers.

Contribution

It introduces the first explainable deep-learning framework leveraging polarization features for automated microplastic fiber classification.

Findings

Achieved 96.7% accuracy on validation data.

Identified eigenvalue ratios as key predictors for classification.

Reduced feature model retained high accuracy of 93.3%.

Abstract

Reliable identification of microplastic fibers is crucial for environmental monitoring but remains analytically challenging. We report an explainable deep-learning framework for classifying microplastic and natural microfibers using polarization-resolved digital holographic microscopy. From multiplexed holograms, the complex Jones matrix of each fiber was reconstructed to extract polarization eigen-parameters describing optical anisotropy. Statistical descriptors of nine polarization characteristics formed a 72-dimensional feature vector for a total of 296 fibers spanning six material classes, including polyamide 6, polyethylene terephthalate, polyamide 6.6, polypropylene, cotton and wool. The designed fully connected deep neural network achieved an accuracy of 96.7 % on the validation data, surpassing that of common machine-learning classifiers. Explainable artificial intelligence analysis with Shapley additive explanations identified eigenvalue-ratio quantities as dominant predictors, revealing the physical basis for classification. An additional reduced-feature model with the preserved architecture exploiting only these most significant eigenvalue-based characteristics retained high accuracy (93.3 %), thereby confirming their dominant role while still outperforming common machine-learning classifiers. These results establish polarization-based features as distinctive optical fingerprints and demonstrate the first explainable deep-learning approach for automated microplastic fiber identification.