Interpretable machine learning assisted spectroscopy for fast characterization of biomass and waste. (1st April 2023)

• Record Type: Journal Article
• Authors: Liang, Rui; Chen, Chao; Sun, Tingxuan; Tao, Junyu; Hao, Xiaoling; Gu, Yude; Xu, Yaru; Yan, Beibei; Chen, Guanyi
• Is Part Of: Waste management. Volume 160(2023)
• Page Start: 90
• Page End: 100
• Publication Date: 2023-04-01
• Subjects: Interpretable machine learning -- Feature selection -- Biomass and waste -- Elemental composition -- Heating value; Hazardous wastes -- Periodicals; Refuse and refuse disposal -- Periodicals; 363.728
• DOI: 10.1016/j.wasman.2023.02.012
• Languages: English
• ISSNs: 0956-053X

Abstract

Graphical abstract: Highlights: This paper discussed the chemical insights behind BW fast characterization method. A novel dimensional reduction method with physical significance was proposed. The performance of the novel dimensional reduction method was compared with PCA. The fundamentals of the input spectra on the output characteristics were explored. Abstract: The combination of machine learning and infrared spectroscopy was reported as effective for fast characterization of biomass and waste (BW). However, this characterization process is lack of interpretability towards its chemical insights, leading to less satisfactory recognition for its reliability. Accordingly, this paper aimed to explore the chemical insights of the machine learning models in the fast characterization process. A novel dimensional reduction method with significant physicochemical meanings was thus proposed, where the high loading spectral peaks of BW were selected as input features. Combined with functional groups attribution of these spectral peaks, the machine learning models established based on the dimensionally reduced spectral data could be explained with clear chemical insights. The performance of classification and regression models between the proposed dimensional reduction method and principal component analysis method was compared. The influence mechanism of each functional group on the characterization results were discussed. CH deformation, CC stretch & CO stretch and ketone/aldehyde CO stretch played essential roles in C, H/ LHV and O prediction, respectively. The results of this work demonstrated the theoretical fundamentals of the machine learning and spectroscopy based BW fast characterization method.