ABSTRACT

Oxalic acid is one of the important organic acids produced by fermentation and its production is affected by several factors. This study investigated the effect of three independent variables namely; potassium dihydrogen phosphate (KH₂PO₄), magnesium sulphate (MgSO₄) and sodium nitrate (NaNO₃) and their mutual interactions on oxalic acid production from pineapple waste in a Box Behnken design. Modelling was carried out using response surface methodology (RSM) and artificial neural network (ANN). A quadratic model was obtained to predict the concentration of oxalic acid as a function of the three independent variables from RSM. For ANN, incremental back propagation (IBP) with hyperbolic tangent function (Tanh) for both hidden and output layers was the best model for predicting oxalic acid production. The developed RSM and ANN models described the fermentation with high accuracy as indicated by their high R² (0.9570 and 0.9894 respectively), low RMSE (1.0923 and 0.5417 respectively) and low AAD (7.8692 and 1.1887 respectively). RSM and ANN were applied to optimize the process for best operating condition and ANN gave the maximum value of oxalic acid (20.725  g/L) with the best combination of the input variables (0.77 g/L of KH₂PO₄, 0.09 g/L of MgSO₄ and 1.78 g/L of NaNO₃). Based on the statistical indices used for evaluation, ANN performed better than RSM.