Neural network prediction of biomass digestibility based on structural features

Plots of biomass digestibility are linear with the natural logarithm of enzyme loading; the slope and intercept characterize biomass reactivity. The feed-forward back-propagation neural networks were performed to predict biomass digestibility by simulating the 1-, 6-, and 72-h slopes and intercepts of glucan, xylan, and total sugar hydrolyses of 147 poplar wood model samples with a variety of lignin contents, acetyl contents, and crystallinity indices. Regression analysis of the neural network models indicates that they performed satisfactorily. Increasing the dimensionality of the neural network input matrix allowed investigation of the influence glucan and xylan enzymatic hydrolyses have on each other. Glucan hydrolysis affected the last stage of xylan digestion, and xylan hydrolysis had no influence on glucan digestibility. This study has demonstrated that neural networks have good potential for predicting biomass digestibility over a wide range of enzyme loadings, thus providing the potential to design cost-effective pretreatment and saccharification processes.