A combined artificial neural network modeling–particle swarm optimization strategy for improved production of marine bacterial lipopeptide from food waste

• The combined ANN–PSO strategy leads to the lipopeptide yield of 6.58 ± 0.32 g L−1.
• ANN–PSO approach resulted in the enhancement of lipopeptide production by 46% (w/v).
• With NPW, the operating cost decreased 20 times when compared with synthetic medium.

In the present study, an artificial neural network (ANN) modeling coupled with particle swarm optimization (PSO) algorithm was used to optimize the process variables for enhanced lipopeptide production by marine Bacillus megaterium, using food waste. In the non-linear ANN model, temperature, pH, agitation and aeration were used as input variables and lipopeptide concentration as the output variable. Further, on application of PSO to the ANN model, the optimum values of the process parameters were as follows: pH = 6.7, temperature = 33.3 °C, agitation rate = 458 rpm and aeration rate = 128 L h−1. Significant enhancement of lipopeptide production from waste by about 46% (w/v) with 20 times reduction in operating cost compared to the conventional synthetic medium was achieved under optimum conditions. Thus, the novelty of the work lies in the application of combination of ANN–PSO as optimization strategy to enhance the yield of a fermentative product like lipopeptide biosurfactant from waste.