Machine-learning-aided thermochemical treatment of biomass: a review

Abstract

Thermochemical treatment is a promising technique for biomass disposal and valorization. Recently, machine learning (ML) has been extensively used to predict yields, compositions, and properties of biochar, bio-oil, syngas, and aqueous phases produced by the thermochemical treatment of biomass. ML demonstrates great potential to aid the development of thermochemical processes. The present review aims to 1) introduce the ML schemes and strategies as well as descriptors of the input and output features in thermochemical processes; 2) summarize and compare the up-to-date research in both ML-aided wet (hydrothermal carbonization/liquefaction/gasification) and dry (torrefaction/pyrolysis/gasification) thermochemical treatment of biomass (i.e., predicting the yields, compositions, and properties of oil/char/gas/aqueous phases as well as thermal conversion behavior or kinetics); and 3) identify the gaps and provide guidance for future studies concerning how to improve predictive performance, increase generalizability, aid mechanistic and application studies, and effectively share data and models in the community. The development of biomass thermochemical treatment processes is envisaged to be greatly accelerated by ML in the near future.

Harnessing a Better Future: Exploring AI and ML Applications in Renewable Energy

“…This can be accomplished via the study of biomass availability, growth patterns, and quality. The goal is to increase biomass output while simultaneously reducing environmental damage [361].  Improving the Logistics of the Biomass Supply Chain:…”

Co-Gasification of Pistachio Shells with Wood Pellets in a Semi-Industrial Hybrid Cross/Updraft Reactor for Producer Gas and Biochar Production

“…Gasification is one of the most feasible thermochemical processes, besides pyrolysis and torrefaction, for producing high-quality, sustainable, multi-purpose materials that can widely replace fossil fuel-based materials in many applications [1][2][3]. The equivalence ratio (ER) usually ranges from 0.1 to 0.5, while process temperatures are held between 650 and 1200 • C [4,5] depending on the gasification principle (fixed bed [6], fluidised bed [7], or entrained flow [8]). The gasification media includes air, steam, CO 2 , or their mixtures [9][10][11][12].…”

Machine Learning Model Insights into Base-Catalyzed Hydrothermal Lignin Depolymerization

“…Inspired by the recent developments in the usage of ML in the study of thermochemical and hydrothermal conversion of biomass, , in this study, base-catalyzed and non-catalyzed hydrothermal depolymerization of lignin was investigated, for the first time, by combining ML modeling to predict the yield of bio-oil and solid residue and experimental work to test the validity of the models. Explainable variable importance for the models was obtained through two different methodologies in order to obtain insight into how the process variables in lignin depolymerization impact the results of the experiments.…”