This paper reviews the current technological development of bio-hydrogen (BioH₂) generation, focusing on using lignocellulosic feedstock via dark fermentation (DF). Using the collected reference reports as the training data set, supervised machine learning via the constructed artificial neuron networks (ANNs) imbedded with feed backward propagation and one cross-out validation approach was deployed to establish correlations between the carbon sources (glucose and xylose) together with the inhibitors (acetate and other inhibitors, such as furfural and aromatic compounds), hydrogen yield (HY), and hydrogen evolution rate (HER) from reported works. Through the statistical analysis, the concentrations variations of glucose (F-value = 0.0027) and acetate (F-value = 0.0028) were found to be statistically significant among the investigated parameters to HY and HER. Manipulating the ratio of glucose to acetate at an optimal range (approximate in 14:1) will effectively improve the BioH₂ generation (HY and HER) regardless of microbial strains inoculated. Comparative studies were also carried out on the evolutions of electron equivalent balances using lignocellulosic biomass as substrates for BioH₂ production across different reported works. The larger electron sinks in the acetate is found to be appreciably related to the higher HY and HER. To maintain a relative higher level of the BioH₂ production, the biosynthesis needs to be kept over 30% in batch cultivation, while the biosynthesis can be kept at a low level (2%) in the continuous operation among the investigated reports. Among available solutions for the enhancement of BioH₂ production, the selection of microbial strains with higher capacity in hydrogen productions is still one of the most phenomenal approaches in enhancing BioH₂ production. Other process intensifications using continuous operation compounded with synergistic chemical additions could deliver additional enhancement for BioH₂ productions during dark fermentation.

In this work, the impact of chemical additions, especially nano-particles (NPs), was quantitatively analyzed using our constructed artificial neural networks (ANNs)-response surface methodology (RSM) algorithm. Fe-based and Ni-based NPs and ions, including Mg²⁺, Cu²⁺, Na⁺, NH₄⁺, and K⁺, behave differently towards the response of hydrogen yield (HY) and hydrogen evolution rate (HER). Manipulating the size and concentration of NPs was found to be effective in enhancing the HY for Fe-based NPs and ions, but not for Ni-based NPs and ions. An optimal range of particle size (86–120 nm) and Ni-ion/NP concentration (81–120 mg L⁻¹) existed for HER. Meanwhile, the manipulation of the size and concentration of NPs was found to be ineffective for both iron and nickel for the improvement of HER. In fact, the variation in size of NPs for the enhancement of HY and HER demonstrated an appreciable difference. The smaller (less than 42 nm) NPs were found to definitely improve the HY, whereas for the HER, the relatively bigger size of NPs (40–50 nm) seemed to significantly increase the H₂ evolution rate. It was also found that the variations in the concentration of the investigated ions only statistically influenced the HER, not the HY. The level of response (the enhanced HER) towards inputs was underpinned and the order of significance towards HER was identified as the following: Na⁺ > Mg²⁺ > Cu²⁺ > NH₄⁺ > K⁺.

The current hydrogen generation technologies, especially biomass gasification using fluidized bed reactors (FBRs), were rigorously reviewed. There are involute operational parameters in a fluidized bed gasifier that determine the anticipated outcomes for hydrogen production purposes. However, limited reviews are present that link these parametric conditions with the corresponding performances based on experimental data collection. Using the constructed artificial neural networks (ANNs) as the supervised machine learning algorithm for data training, the operational parameters from 52 literature reports were utilized to perform both the qualitative and quantitative assessments of the performance, such as the hydrogen yield (HY), hydrogen content (HC) and carbon conversion efficiency (CCE). Seven types of operational parameters, including the steam-to-biomass ratio (SBR), equivalent ratio (ER), temperature, particle size of the feedstock, residence time, lower heating value (LHV) and carbon content (CC), were closely investigated. Six binary parameters have been identified to be statistically significant to the performance parameters (hydrogen yield (HY)), hydrogen content (HC) and carbon conversion efficiency (CCE) by analysis of variance (ANOVA). The optimal operational conditions derived from the machine leaning were recommended according to the needs of the outcomes. This review may provide helpful insights for researchers to comprehensively consider the operational conditions in order to achieve high hydrogen production using fluidized bed reactors during biomass gasification.