Statistical comparison of two modeling methods on pressurized hot water extraction of vitamin C and phenolic compounds from Moringa oleifera leaves

Abstract

Moringa oleifera is an excellent source of bioactive compounds which exhibit nutritional and medicinal properties. Pressurized hot water extraction is known as a green, environmentally, faster and efficient extraction technique. However, it is facing a challenge with the degradation of thermolabile compounds at higher temperature. This research was performed to investigate the influence of extraction temperature, time and flow rate of pressurized hot water extraction in the recovery of Vitamin C and phenolic compounds from Moringa oleifera leaves. Response surface methodology (RSM) and artificial neural network (ANN) were used as estimates and predictive models with maximum responses. The optimal pressurized hot water extraction conditions were identified at: 91°C for temperature, 60 min for extraction time and 0.3 mL min−1 for flow rate, giving a predicted concentration of 3.92 ± 0.30, 4.74 ± 0.32 and 0.357 ± 0.19 g per 100 g of dry powder for kaempferol, quercetin and vitamin C, respectively. Evaluation of the two models through the statistical error parameters showed that ANN model gave a good predictive and estimation capabilities than RSM. Therefore, ANN can be recommended for use optimization method in the pressure hot water extraction.