Optimization strategies for improved biogas production by recycling of waste through response surface methodology and artificial neural network: Sustainable energy perspective research

Objective: The primary aim of the study is to augment the biogas production from flower waste through optimization and pretreatment techniques. Methods: Enhancement of biogas production by using response surface methodology (RSM) and artificial neural network (ANN) was done. The time for agitation, the concentration of the substrate, temperature and pH were considered as model variables to develop the predictive models. Pretreatment of withered flowers was studied by using physical, chemical, hydrothermal and biological methods. Results: The linear model terms of concentration of substrate, temperature, pH, and time for agitation had effects of interaction (p < 0.05) significantly. From the ANN model, the optimal parameters for the biogas production process increased when equaled to the model of RSM. It indicates that the artificial neural network model is predicting the yield of biogas efficiently and accurately than the RSM model. Chemical pre-treatments were found to enhance the biogas production from flower waste with higher biomethane kinetics and cumulative yield. Conclusion: Biogas production was significantly improved with statistical optimization and pretreatment techniques. (C) 2020 The Author(s). Published by Elsevier B.V. on behalf of King Saud University.

Automated summary

The study aims to increase biogas production from flower waste through optimization and pretreatment techniques, with chemical pretreatment found to enhance biomethane kinetics and cumulative yield. The use of artificial neural networks proved to be more efficient and accurate in predicting biogas yield compared to response surface methodology.