Third generation biomass (marine macroalgae) has been projected as a promising alternative energy resource for bioethanol production due to its high carbon and no lignin composition. However, the major challenge in the technologies of production lies in the fermentative bioconversion process. Therefore, in the present study the predictive ability of an integrated artificial neural network with genetic algorithm (ANN-GA) in the modelling of bioethanol production was investigated for an indigenous marine macroalgal biomass (Ulva prolifera) by a novel yeast strain, Saccharomyces cerevisiae NFCCI1248 using six fermentative parameters, viz., substrate concentration, fermentation time, inoculum size, temperature, agitation speed and pH. The experimental model was developed using one-variable-at-a-time (OVAT) method to analyze the effects of the fermentative parameters on bioethanol production and the obtained regression equation was used as a fitness function for the ANN-GA modelling. The ANN-GA model predicted a maximum bioethanol production at 30 g/L substrate, 48 h fermentation time, 10% (v/v) inoculum, 30 °C temperature, 50 rpm agitation speed and pH 6. The maximum experimental bioethanol yield obtained after applying ANN-GA was 0.242 ± 0.002 g/g RS, which was in close proximity with the predicted value (0.239 g/g RS). Hence, the developed ANN-GA model can be applied as an efficient approach for predicting the fermentative bioethanol production from macroalgal biomass.
All Science Journal Classification (ASJC) codes
- Environmental Engineering
- Environmental Chemistry
- Waste Management and Disposal