RECYCLING-ORIENTED IDENTIFICATION OF FOSSIL-BASED PLASTICS AND BIOPLASTICS IN PACKAGING WASTE USING HYPERSPECTRAL IMAGING AND HIERARCHICAL CLASSIFICATION
- Giuseppe Bonifazi - Department of Chemical Engineering, Materials & Environment, Sapienza University of Rome, Italy
- Giuseppe Capobianco - Department of Chemical Engineering, Materials & Environment, Sapienza University of Rome, Italy
- Paola Cucuzza - Department of Chemical Engineering, Materials & Environment, University of Rome La Sapienza, Italy
- Silvia Serranti - Department of Chemical Engineering, Materials & Environment, Sapienza University of Rome, Italy
- Available online in Detritus - In Press
- Pages
Released under All rights reserved
Copyright: © 2026 CISA Publisher
Abstract
The increasing use of bioplastics in packaging leads to their presence within conventional plastic waste streams, where even minor cross-contamination can compromise recycled material quality. Therefore, rapid and efficient material identification strategies are required to support high-purity sorting processes. This study evaluates the applicability of short-wave infrared hyperspectral imaging (SWIR-HSI: 1000–2500 nm) combined with chemometric and machine-learning approaches for the automatic classification of fossil-based plastic and bioplastic flakes from household packaging waste. Five fossil-based polymers commonly used for plastic packaging, i.e., polyethylene terephthalate (PET), high-density polyethylene (HDPE), polypropylene (PP), polystyrene (PS), expanded polystyrene (EPS), and three polylactic acid (PLA)-based bioplastics derived from disposable food packaging items were investigated. Hyperspectral images of the studied samples were acquired in the SWIR range and divided into calibration and validation datasets to develop and evaluate the proposed classification model. After spectral preprocessing, Principal Component Analysis (PCA) was used to explore class separability and guide the development of a hierarchical Partial Least Squares-Discriminant Analysis (Hi-PLS-DA) model. The proposed methodology achieved high predictive performance on the independent validation dataset, with sensitivity and specificity ranging from 0.96 to 1.00. Although conceived as a proof of concept, the proposed approach demonstrates the feasibility of combining SWIR-HSI with hierarchical chemometric classification for recycling-oriented identification of fossil-based plastics and PLA-based bioplastics, supporting the development of more effective sensor-based sorting strategies.Keywords
Editorial History
- Received: 07 Jul 2026
- Revised: 07 Sep 2026
- Accepted: 10 Sep 2026
- Available online: 20 Sep 2026
References
Alaerts, L., Augustinus, M., & Van Acker, K. (2018). Impact of bio-based plastics on current recycling of plastics. Sustainability (Switzerland), 10(5).
DOI 10.3390/su10051487
Araujo-Andrade, C., Bugnicourt, E., Philippet, L., Rodriguez-Turienzo, L., Nettleton, D., Hoffmann, L., & Schlummer, M. (2021). Review on the photonic techniques suitable for automatic monitoring of the composition of multi-materials wastes in view of their posterior recycling. Waste management & research, 39(5), 631-651
Ballabio, D., and Todeschini, R., (2009). Multivariate classification for qualitative analysis, New York In D.-W. Sun (Ed.). Infrared spectroscopy for quality analysis and control, 83–104
Ballabio, D. and Consonni, V., (2013). Classification tools in chemistry. Part 1: Linear models. PLS-DA, Analytical Methods, 5, 3790-3798
Barker, M., Rayens, W., (2003). Partial least squares for discrimination. Journal of Chemometrics, 17 (3), 166–173.
DOI 10.1002/cem.785
Bonifazi, G., Capobianco, G., Cucuzza, P., Serranti, S., & Uzzo, A. (2022). Recycling-oriented characterization of the PET waste stream by SWIR hyperspectral imaging and variable selection methods. Detritus, 18, 42-49
Bonifazi, G., Capobianco, G., Cucuzza, P., & Serranti, S. (2025a). Contaminant detection in flexible polypropylene packaging waste using hyperspectral imaging and machine learning. Waste Management, 195, 264-274
Bonifazi, G., Capobianco, G., Cucuzza, P., & Serranti, S. (2025b, May). Application of hyperspectral imaging for identifying polymer blends in polypropylene flexible packaging waste for enhanced recycling. In Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imaging XXXI (Vol. 13455, pp. 266-274). SPIE
Bro, R., Smilde, A.K., (2014). Principal component analysis. Analytical Methods, 6, 2812.
DOI 10.1039/c3ay41907j
Cheng, M. F., Mukundan, A., Karmakar, R., Valappil, M. A. E., Jouhar, J., & Wang, H. C. (2025). Modern trends and recent applications of hyperspectral imaging: A review. Technologies, 13(5), 170
Cosate de Andrade, M. F., Souza, P. M., Cavalett, O., & Morales, A. R. (2016). Life cycle assessment of poly (lactic acid)(PLA): Comparison between chemical recycling, mechanical recycling and composting. Journal of Polymers and the Environment, 24(4), 372-384
Das, A., Mishra, S., Tripathy, B. (2025). Bioplastics: a sustainable alternative or a hidden microplastic threat?. Innovative Infrastructure Solutions. 10(7), 321
Cucina, M., De Nisi, P., Trombino, L., Tambone, F., & Adani, F. (2021). Degradation of bioplastics in organic waste by mesophilic anaerobic digestion, composting and soil incubation. Waste Management, 134, 67-77
De Gisi, S., Gadaleta, G., Gorrasi, G., La Mantia, F. P., Notarnicola, M., & Sorrentino, A. (2022). The role of (bio) degradability on the management of petrochemical and bio-based plastic waste. Journal of Environmental Management, 310, 114769
Eigenvector Research, 2011. Mncn. https://www.eigenvectordocs.com/index.php?title=Mncn (accessed on 01 May 2026)
Eigenvector Research, 2013. Gapsegment. https://www.eigenvectordocs.com/index.php?title=Gapsegment#Purpose (accessed on 01 May 2026)
Eigenvector Research, 2018. Confusionmatrix. https://www.eigenvectordocs.com/index.php?title=Confusionmatrix (accessed on 01 May 2026)
Eigenvector Research, 2019. Advanced Preprocessing: Noise, Offset, and Baseline Filtering. https://www.eigenvectordocs.com/index.php?title=Advanced_Preprocessing:_Noise,_Offset,_and_Baseline_Filtering#Detrend (last accessed on 01 May 2026)
Eigenvector Research, 2021. Advanced Preprocessing: Sample Normalization. https://www.eigenvectordocs.com/index.php?title=Advanced_Preprocessing:_Sample_Normalization (accessed on 01 May 2026)
Eigenvector Research, 2024. Crossval. https://www.eigenvectordocs.com/index.php?title=Crossval (accessed on 01 May 2026)
Eigenvector Research, 2025. T-Squared Q residuals and Contributions. https://www.eigenvectordocs.com/index.php?title=T-Squared_Q_residuals_and_Contributions (accessed on 01 May 2026)
European Bioplastics, 2025. Article 9 PPWR – Why certain packaging formats should be compostable. https://www.european-bioplastics.org/article-9-ppwr-why-certain-packaging-formats-should-be-compostable/ (accessed on 02 May 2026)
European Commission, 2024. Packaging and packaging waste regulation (PPWR). https://environment.ec.europa.eu/document/download/63fd2c88-e85a-412c-bcf4-372eff99008a_en (accessed on 02 May 2026)
Gadaleta, G., Ferrara, C., De Gisi, S., Notarnicola, M., & De Feo, G. (2023). Life cycle assessment of end-of-life options for cellulose-based bioplastics when introduced into a municipal solid waste management system. Science of the Total Environment, 871, 161958
Lavagnolo, M.C., Ruggero, F., Pivato, A., Boaretti, C., Chiumenti, A. (2020). Composting of starch-based bioplastic bags: small scale test of degradation and size reduction trend. Detritus. 57–65
Li, M., Cai, Q., Zhang, T., Tang, H., & Li, H. (2025). Progress of complex system process analysis based on modern spectroscopy combined with chemometrics. Journal of Chemometrics, 39(2), e70006
McLauchlin, A. R., Ghita, O., & Gahkani, A. (2014). Quantification of PLA contamination in PET during injection moulding by in-line NIR spectroscopy. Polymer Testing, 38, 46-52
Pottinger, A. S., Geyer, R., Biyani, N., Martinez, C. C., Nathan, N., Morse, M. R., Shanying Hu, C. L., de Bruyn, M., Boettiger, C., Baker, E., & McCauley, D. J. (2024). Pathways to reduce global plastic waste mismanagement and greenhouse gas emissions by 2050. Science, 386(6726), 1168-1173
Rinnan, Å., van den Berg, F.M., Engelsen, S.B., 2009. Review of the most common pre-processing techniques for near-infrared spectra, TrAC Trends Anal. Chem, 28, pp. 1201-1222
Serranti, S., Cucuzza, P., & Bonifazi, G. (2020, November). Hyperspectral imaging for VIS-SWIR classification of post-consumer plastic packaging products by polymer and color. In SPIE Future Sensing Technologies (Vol. 11525, pp. 212-217). SPIE
Serranti, S., Bonifazi, G., Cocozza, P., Cucuzza, P., Palmieri, R., Benzi, M., Lezzi M., Mazziotti C., Riccardi E., Barbieri E., Ingrando I., & Moroni, F. (2026). Comparison of hyperspectral imaging and FTIR spectroscopy for microplastic polymer identification: Proposal of a scalable protocol validated in a 12-month river survey. Talanta, 129361
Taneepanichskul, N., Hailes, H. C., & Miodownik, M. (2025). Using hyperspectral imaging and machine learning to identify food-contaminated compostable and recyclable plastics. UCL Open Environment, 7.
DOI 10.14324/111.444/ucloe.3237
Ulrici, A., Serranti, S., Ferrari, C., Cesare, D., Foca, G., & Bonifazi, G. (2013). Efficient chemometric strategies for PET–PLA discrimination in recycling plants using hyperspectral imaging. Chemometrics and Intelligent Laboratory Systems, 122, 31-39
Vidal, M., Amigo, J.M., (2012). Pre-processing of hyperspectral images. Essential steps before image analysis. Chemometrics and Intelligent Laboratory Systems, 117, pp. 138-148.
DOI 10.1016/j.chemolab.2012.05.009