Machine Learning and Hyperspectral Imaging-Aided Forecast for the Share of Biogenic and Fossil Carbon in Solid Waste

Abstract

Traditional methods for analyzing the biogenic and fossil carbon shares in solid waste are time-consuming and labor-intensive. A novel approach was developed to directly classify the carbon group and predict carbon content using the hyperspectral imaging (HSI) spectra of solid waste in conjunction with state-of-the-art tree-based machine learning models, including random forest (RF), extreme gradient boost, and light gradient boost machine (LGBM). All of the classifiers and regressors were able to achieve an accuracy above 0.95 and an R2 of 0.96 in the test set, respectively. In addition, two model interpretation approaches, the Shapley additive explanation and model explainer, were applied. The results showed that the predictions of the developed models were based on a reasonable understanding of the overtone and shake of the functional groups (C–H, N–H, and O–H). Furthermore, the developed models were validated by an external test set, which did not overlap with the data used for model construction. The RF and LGBM showed robust performance with a 0.790 accuracy for carbon group classification and a 0.806 R2 for carbon content prediction. Overall, the optimal models provided a rapid method for characterizing the biogenic carbon share in solid waste based on raw HSI spectra without preprocessing.