Fast and robust NIRS-based characterization of raw organic waste: Using non-linear methods to handle water effects. (1st December 2022)

• Record Type: Journal Article
• Authors: Mallet, Alexandre; Charnier, Cyrille; Latrille, Éric; Bendoula, Ryad; Roger, Jean-Michel; Steyer, Jean-Philippe
• Is Part Of: Water research. Volume 227(2022)
• Publication Date: 2022-12-01
• Subjects: Near infrared spectroscopy -- Anaerobic digestion -- Biochemical methane potential -- Water effects -- Non-linear modeling, Neural network; Water -- Pollution -- Research -- Periodicals; 363.7394
• DOI: 10.1016/j.watres.2022.119308
• Languages: English
• ISSNs: 0043-1354

Abstract

Highlights: Multiple non-linear methods are evaluated for raw organic waste characterization. Local linear models and non-linear models override water effects. Calibrations on raw samples (no drying or grinding) were successfully built. This opens the door to at-site NIRS-based characterization of raw organic waste. Abstract: Fast characterization of organic waste using near infrared spectroscopy (NIRS) has been successfully developed in the last decade. However, up to now, an on-site use of this technology has been hindered by necessary sample preparation steps (freeze-drying and grinding) to avoid important water effects on NIRS. Recent research studies have shown that these effects are highly non-linear and relate both to the biochemical and physical properties of samples. To account for these complex effects, the current study compares the use of many different types of non-linear methods such as partial least squares regression (PLSR) based methods (global, clustered and local versions of PLSR), machine learning methods (support vector machines, regression trees and ensemble methods) and deep learning methods (artificial and convolutional neural networks). On an independent test data set, non-linear methods showed errors 28% lower than linear methods. The standard errors of prediction obtained for the prediction of total solids content (TS%), chemical oxygen demand (COD) and biochemical methane potential (BMP) were respectively 8%, 160 mg(O2 ).gTS −1 and 92 mL(CH4 ).gTS −1 . These latter errors are similar to successful NIRS applications developed on freeze-dried samples. These findings hold great promises regarding the development of at-site and online NIRS solutions in anaerobic digestion plants. Graphical abstract: Graphical Abstract – A comprehensive comparison of non-linear calibration methods for NIRS-based characterization of diverse organic waste in raw form. Image, graphical abstract