A machine learning assisted prediction of potential biochar and its applications in anaerobic digestion for valuable chemicals and energy recovery from organic waste

Abstract

The utilization of biochar derived from biomass residue to enhance anaerobic digestion (AD) for bioenergy recovery offers a sustainable approach to advance sustainable energy and mitigate climate change. However, conducting comprehensive research on the optimal conditions for AD experiments with biochar addition poses a challenge due to diverse experimental objectives. Machine learning (ML) has demonstrated its effectiveness in addressing this issue. Therefore, it is essential to provide an overview of current ML-optimized energy recovery processes for biochar-enhanced AD in order to facilitate a more systematic utilization of ML tools. This review comprehensively examines the material and energy flow of biochar preparation and its impact on AD is comprehension reviewed to optimize biochar-enhanced bioenergy recovery from a production process perspective. Specifically, it summarizes the application of the ML techniques, based on artificial intelligence, for predicting biochar yield and properties of biomass residues, as well as their utilization in AD. Overall, this review offers a comprehensive analysis to address the current challenges in biochar utilization and sustainable energy recovery. In future research, it is crucial to tackle the challenges that hinder the implementation of biochar in pilot-scale reactors. It is recommended to further investigate the correlation between the physicochemical properties of biochar and the bioenergy recovery process. Additionally, enhancing the role of ML throughout the entire biochar-enhanced bioenergy recovery process holds promise for achieving economically and environmentally optimized bioenergy recovery efficiency.