Machine Learning-Based Identification of Plastic Types Using Handheld Spectrometers
Sensors · 2025-06-17 · 25 (12) · 3777
DOI: 10.3390/s25123777 ↗At a glance
Journal article in Sensors, published online on 2025-06-17. Written by Hedde van Hoorn and 5 co-authors. Institution: Photonics Research Group, The Hague University of Applied Sciences, 2628 AL Delft, The Netherlands. Cited 14 times so far (Crossref); 18 references. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
Plastic waste and pollution is growing rapidly worldwide and most plastics end up in landfill or are incinerated because high-quality recycling is not possible. Plastic-type identification with a low-cost, handheld spectral approach could help in parts of the world where high-end spectral imaging systems on conveyor belts cannot be implemented. Here, we investigate how two fundamentally different handheld infrared spectral devices can identify plastic types by benchmarking the same analysis against a high-resolution bench-top spectral approach. We used the handheld Plastic Scanner, which measures a discrete infrared spectrum using LED illumination at different wavelengths, and the SpectraPod, which has an integrated photonics chip which has varying responsivity in different channels in the near-infrared. We employ machine learning using SVM, XGBoost, Random Forest and Gaussian Naïve Bayes models on a full dataset of plastic samples of PET, HDPE, PVC, LDPE, PP and PS, with samples of varying shape, color and opacity, as measured with three different experimental approaches. The high-resolution spectral approach can obtain an accuracy (mean ± standard deviation) of (0.97 ± 0.01), whereas we obtain (0.93 ± 0.01) for the SpectraPod and (0.70 ± 0.03) for the Plastic Scanner. Differences of reflectance at subsequent wavelengths prove to be the most important features in the plastic-type classification model when using high-resolution spectroscopy, which is not possible with the other two devices. Lower accuracy for the handheld devices is caused by their limitations, as the spectral range of both devices is limited—up to 1600 nm for the SpectraPod, while the Plastic Scanner has limited sensitivity to reflectance at wavelengths of 1100 and 1350 nm, where certain plastic types show characteristic absorbance bands. We suggest that combining selective sensitivity channels (as in the SpectraPod) and illuminating the sample with varying LEDs (as with the Plastic Scanner) could increase the accuracy in plastic-type identification with a handheld device.
Subjects
Author keywords
Authors and institutions
- Photonics Research Group, The Hague University of Applied Sciences, 2628 AL Delft, The Netherlands.
- AI & Data Science Expert Group, The Hague University of Applied Sciences, 2628 AL Delft, The Netherlands.
- Plastic Scanner Project, 2611 AN Delft, The Netherlands.
ORCID profiles: Hedde van Hoorn, Arie-Willem de Leeuw, Amey Vasulkar, Jerry de Vos, Steven van den Berg
Cite
APA
van Hoorn, H., Pourmohammadi, F., de Leeuw, A. W., Vasulkar, A., de Vos, J., & van den Berg, S. (2025). Machine Learning-Based Identification of Plastic Types Using Handheld Spectrometers. Sensors, 25(12), 3777. https://doi.org/10.3390/s25123777
Vancouver
van Hoorn H, Pourmohammadi F, de Leeuw AW, Vasulkar A, de Vos J, van den Berg S. Machine Learning-Based Identification of Plastic Types Using Handheld Spectrometers. Sensors. 2025;25(12):3777. doi:10.3390/s25123777
BibTeX
@article{vanHoorn2025,
author = {van Hoorn, Hedde and Pourmohammadi, Fahimeh and de Leeuw, Arie-Willem and Vasulkar, Amey and de Vos, Jerry and van den Berg, Steven},
title = {Machine Learning-Based Identification of Plastic Types Using Handheld Spectrometers},
journal = {Sensors},
year = {2025},
volume = {25},
number = {12},
pages = {3777},
doi = {10.3390/s25123777}
}
EUVIMED