Prediction of Hydrogen Production Rate in Anaerobic Fermentation Using Grey Relation Analysis and Machine Learning

Abstract

Anaerobic fermentation for hydrogen production has many environmental factors that limit microbial activity, but machine learning has enormous potential in handling the complexity of biological processes. This study explores the potential of machine learning in predicting hydrogen production rates (HPR) from anaerobic fermentation of biomass energy. Grey relation analysis was conducted to determine the correlation between operational parameters and HPR. Five machine learning algorithms, such as decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost), and K-nearest neighbor (KNN), were then paired with operating conditions and water quality performance as features and HPR as a label, with mean squared error (MSE) and R2 as evaluation indexes. Butyric acid, oxidation-reduction potential (ORP), and volatile suspended solids (VSS) were found to play crucial roles in hydrogen production from sucrose anaerobic fermentation. XGBoost had the highest accuracy with R2 of 0.91 and MSE of 0.0052.

Keywords: Biohydrogen, Anaerobic fermentation, Grey relation analysis, Machine learning, Prediction model