The accumulation of microplastics (MPs) in different environmental compartments represents a real emergency with dangerous effects on all ecosystems and human health. MPs analysis by the commonly adopted methods (i.e. FT-IR or Raman spectroscopy) is time-consuming, limiting the ability to monitor and mitigate plastic pollution. In this context, hyperspectral imaging (HSI) can be considered a promising identification tool, allowing the possibility to obtain rapid classification maps of MPs in different environmental matrices. In this work, an innovative application of HSI technology in the short-wave infrared range (SWIR: 1000-2500 nm) for rapid recognition and classification of MPs in real beach sand samples, coupled with machine learning approaches, is presented and discussed. MP samples were collected during a sampling campaign at Torre Guaceto beach (southern Italy), located along the Adriatic flank of the Apulia region, belonging to a natural protected area. Different spectral preprocessing strategies were tested on the acquired hyperspectral images in order to build a classification model capable of recognizing the complex mixture of materials that constitute MPs and beach sand matrices. The results of the study demonstrated as the proposed approach represents a powerful, fast and effective alternative to the most common adopted analytical methods for MP classification.
Hyperspectral imaging (HSI) is currently more and more utilized in waste recycling industry for both sensor-based sorting and quality control applications. Plastic waste is one of the flow streams in which HSI is particularly effective, due to its high capability of polymer identification in the near and short-wave infrared range, allowing to achieve high purity recycled plastic products and, therefore, secondary raw materials characterized by high quality. The aim of this work was to evaluate the potential of HSI-based data fusion, to achieve simultaneous identification of post-consumer plastic packaging flakes by polymer and color. Five different polymers among those commonly used for plastic packaging, i.e., polystyrene (PS), polyethylene terephthalate (PET), expanded polystyrene (EPS), polyethylene (PE), and polypropylene (PP), subdivided in 6 different color classes (orange, red, transparent, green, blue and white) were investigated. Two different HSI devices were used to perform the polymer and color identification, operating in the short-wave infrared range (1000-2500 nm) and in the visible range (400-750 nm), respectively. A hierarchical classification model based on partial least square - discriminant analysis (PLS-DA) was built in order to obtain a highlevel efficiency in prediction for all classes. The performances of the model were evaluated in terms of sensitivity, specificity, precision and F1 score. The obtained results were very promising, showing how HSI coupled with data fusion can be utilized as a non-invasive, fast and efficient tool to obtain high-quality recycled plastics, optimizing the industrial plastic recycling process.
Improving the quality of recovery and recycling of post-consumer plastic packaging is certainly one of the objectives of the circular economy. Currently, these secondary raw materials still represent only a small part of the materials used in the EU compared to primary ones. Therefore, it is necessary to improve the selection, the separation and recovery techniques with the aim to increase the quantity and quality of these materials put in the market. For these reasons, hyperspectral imaging (HSI) techniques represent a great solution for the characterization, the classification and quality check of different secondary raw materials in several industrial sectors. The present study proposes an efficient characterization of the most used polyolefins, polyethylene (PE) and polypropylene (PP), derived from post-consumer plastic packaging, based on the type of polymer and color, through HSI analysis and the implementation of classification models. Two different HSI acquisition tools were used, working in the short-wave infrared range (1000-2500 nm), to determinate the polymer, and in the visible range (400-700 nm) for the identification by color. In addition, the data processing and the chemometric techniques, used for the development of the classification strategies, have been performed with the PLS_toolbox (Eigenvector Research, Inc.) in Matlab (The MathWorks, Inc.) environment. The obtained results proved the correct identification of the polymer and the color of the investigated plastic flakes, confirming the sustainability and great potential of the HSI analysis techniques, which can be implemented to improve the quality of the plastic materials produced in the recycling plants of polyolefins.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.