Biomethane yield modeling and optimization from thermally pretreated Arachis hypogea shells using response surface methodology and artificial neural network

Biomethane production from thermally pretreated Arachis hypogea shells was modeled using response surface methodology (RSM) and artificial neural network (ANN). RSM and ANN models were investigated based on; temperature, retention time, and pretreatment conditions as input variables, and biomethane yield as the response. The ANN model gave the best performance with Root Mean Square Error (RMSE), Mean Absolute Deviation (MAD) and Mean Absolute Percentage Error (MAPE) values of 7.183, 3.947, and 8.242. RSM and ANN showed near perfection in predicting the biomethane yield of thermally pretreated Arachis hypogea shells with R² values of 0.7393 and 0.9754, with optimum predicted yield of 53.27 and 64.51 ml, respectively. The study's performance metric showed that the developed ANN model is more accurate and reliable than RSM for optimizing and modeling the biomethane yield of Arachis hypogea shells pretreated with thermal techniques.