Spectral Derivatives Improve FTIR-Based Machine Learning Classification of Plastic Polymers

Abstract

Accurate identification of plastic polymers is essential for effective recycling, quality control, and environmental monitoring. This study assesses how spectral derivative preprocessing affects the classification of six common plastic polymers: Polyethylene Terephthalate (PET), Polyvinyl Chloride (PVC), Polypropylene (PP), Polystyrene (PS), and both High- and Low-Density Polyethylene (HDPE and LDPE), based on Fourier Transform Infrared (FTIR) spectroscopy data acquired at a resolution of 8 (Formula presented.). Using Savitzky–Golay derivatives (orders 0, 1, and 2), five machine learning algorithms, namely Multilayer Perceptron (MLP), Extremely Randomized Trees (ET), Linear Discriminant Analysis (LDA), Support Vector Classifier (SVC), and Random Forest (RF), were tested within a strict framework involving stratified repeated cross-validation and a final hold-out test set to evaluate generalization. The first spectral derivative notably improved the model performance, especially for MLP and SVC, and increased the stability of the ET, LDA, and RF classifiers. The combination of the first derivative with the ET model provided the best results, achieving a mean F1-score of 0.99995 (±0.00033) in cross-validation and perfect classification (1.0 in Accuracy, F1-score, Cohen’s Kappa, and Matthews Correlation Coefficient) on the independent test set. LDA also performed very well, underscoring the near-linear separability of spectral data after derivative transformation. These results demonstrate the value of derivative-based preprocessing and confirm a robust method for creating high-precision, interpretable, and transferable machine learning models for automated plastic polymer identification.