Deep learning for chemometric analysis of plastic spectral data from infrared and Raman databases

Increasing plastic recycling rates is key to addressing pollution. New technologies such as chemometric analysis of spectral data have shown great promises in improving the sorting efficiency boost rates. In this work, a novel deep learning architecture, PolymerSpectraDecisionNet (PSDN) was developed, consisting convolutional neural networks, residual networks and inception decision tree structure. To better represent conditions industry, models were built identify most widely recycled polymers – polyethylene, polypropylene polyethylene terephthalate from open-sourced infrared Raman dataset containing over 20 different polymers. PSDN performed than end-to-end obtaining an accuracy 0.949 0.967 with datasets respectively. The use can also distinguish between weathered unaged polymer samples, accuracies 0.954 for high density 0.906 terephthalate.