ANN based process optimization for the growth kinetic study of Nostoc ellipsosporum NCIM 2786

The present study was conducted on the growth kinetics of Nostoc ellipsosporum NCIM 2786 with an optimized parameter. Artificial Neural Network (ANN) based supervised model was developed to optimize the process parameters and correlate the effects of different parameters on the growth of Nostoc ellipsosporum NCIM 2786. The featured parameters taken for model generation were inoculum size, pH, and the concentration of glucose. In continuation with morphological characterization, the further studies were conducted. The biomass concentration of Nostoc ellipsosporum NCIM 2786 was obtained from the cell dry weight. The maximum dry cell weight of 1g/l was obtained at 4% (v/v) inoculum size; the cyanobacteria showed maximum growth at pH 7.5, with 0.25 g/l of glucose. The statistical study using Origin 2020 showed a 0.05 level of significance with P < 0.001. The specific growth rate obtained without using glucose was 0.0624 d-1, productivity obtained was 0.00012 g/l/d, and the generation time or the doubling time for the growth of Nostoc ellipsosporum NCIM 2786 was 11.11 d. The presence of glucose enhances the specific growth rate from 0.0624 d-1 to 0.2216 d-1, the productivity increased to 0.0227 g/l/d, the maximum biomass increased to 0.522 g/l and the generation time changed from 11.11d to 3.128d. The analysis concluded that supplement glucose in the media enhances the growth of Nostoc ellipsosporum NCIM 2786. Further, the model was generated using COPASI, and simulation was performed.