Machine learning prediction of bio-oil production from the pyrolysis of lignocellulosic biomass: Recent advances and future perspectives

Bio-oil produced through pyrolysis of lignocellulosic biomass has recently received significant attention due to its possible uses as a second-generation biofuel. The yield and characteristics of produced bio-oil are affected by reaction conditions and the type of feedstock that is used. Recently, machine learning (ML) techniques have been widely employed to forecast the performance of the pyrolysis and the characteristics of bi-oil. In this study, a comprehensive review of ML research on bio-oil has been carried out. Regression methods were most frequently employed to build prediction models and the top five ML methods for bio-oil research were random forest, artificial neural network, gradient boosting, support vector regression, and linear regression. The prediction results through the developed models were quite consistent with experiment results. However, studies to data have had limitations such as the used of restricted data, extraction features using their own knowledge, and limited used of ML algorithms. We highlighted the challenges and potential of cutting-edge ML techniques in bio-oil production. •Potential of cutting-edge machine learning methods for bio-oil research.•Regression analysis was the most often utilized machine learning technique.•Due to specific usage of restricted data, limited machine learning was implemented.