?Thermal-dissolution based carbon enrichment? treatment of biomass: Modeling and kinetic study via combined lumped reaction model and machine learning algorithm

The homogenizing pyrolytic method denoted as the "Thermal-dissolution based carbon enrichment (TDCE)" was effective in converting different biomasses into value-added carbon products. However, the product yields from the TDCE process varied greatly despite the biomasses undergoing similar reactions. Consequently, a generalized kinetic study is essential in determining the different kinetic parameters of each biomass. In this study, the lumped reaction model was coupled with machine learning algorithm (ML-LRM) for the general acquisition of these kinetic parameters. 304 yield data of cellulose under different conditions were accurately predicted by the machine learning algorithm and were further utilized for subsequent kinetic modeling. In addition, the derived conversion pathways were quite reliable, as the one from predicted data was similar to that calculated from experimental data (R2 = 0.95) under experimental conditions, but with higher accuracy (R2 > 0.99). Moreover, a novel five-stage reaction mechanism was proposed to quantitatively and qualitatively describe the TDCE process based on the kinetic studies and the pre-proposed reaction mechanism. Consequently, the ML-LRM method was proven to be effective in elucidating the main reactions at any temperature throughout the TDCE treatment and can therefore provide guidance towards directed regulation and practical application of said products.