Machine Learning of polymer types from the spectral signature of Raman spectroscopy microplastics data

TL;DR

The paper tackles the challenge of identifying polymer types in environmentally weathered microplastics using Raman spectroscopy. It develops a preprocessing and augmentation pipeline (normalization, ROC transformation, and binning) and compares multiple ML approaches, with Random Forest delivering the best performance. Augmenting the training data substantially improves accuracy from $89\%$ to $93.81\%$ on the environmentally aged SLoPP-E test set, highlighting the value of data augmentation for small, degraded datasets. The work advances Raman-based polymer typing and has practical implications for ecotoxicology, plastics recycling, and water/food quality assessment.

Abstract

The tools and technology that are currently used to analyze chemical compound structures that identify polymer types in microplastics are not well-calibrated for environmentally weathered microplastics. Microplastics that have been degraded by environmental weathering factors can offer less analytic certainty than samples of microplastics that have not been exposed to weathering processes. Machine learning tools and techniques allow us to better calibrate the research tools for certainty in microplastics analysis. In this paper, we investigate whether the signatures (Raman shift values) are distinct enough such that well studied machine learning (ML) algorithms can learn to identify polymer types using a relatively small amount of labeled input data when the samples have not been impacted by environmental degradation. Several ML models were trained on a well-known repository, Spectral Libraries of Plastic Particles (SLOPP), that contain Raman shift and intensity results for a range of plastic particles, then tested on environmentally aged plastic particles (SloPP-E) consisting of 22 polymer types. After extensive preprocessing and augmentation, the trained random forest model was then tested on the SloPP-E dataset resulting in an improvement in classification accuracy of 93.81% from 89%.

Figures (12)

• Figure 4: Sample for polymethyl methacrylate.
• Figure 5: ROC processed sample for polymethyl methacrylate.
• Figure 6: Binning technique of ROC processed sample for polymethyl methacrylate.
• Figure 7: Improved augmented data (red – original; blue – augmented).
• Figure 8: Accuracy of the model with different bin sizes.