Optimization of microwave-assisted extraction of total polyphenolic compounds from chokeberries by response surface methodology and artificial neural network

Abstract

Abstract Response surface methodology (RSM) and artificial neural network (ANN) were used for modeling and optimizing microwave-assisted extraction (MAE) of total polyphenolic content (TPC) from chokeberries ( Aronia melanocarpa ) as a function of microwave power (300, 450 and 600 W), ethanol concentration (25%, 50% and 75%) and extraction time (5, 10 and 15 min). The set of the optimal operational conditions, as well as the conditions which gave the maximum yield of TPC while minimizing extraction time, solvent and energy consumption, (economic conditions), were proposed. Statistical indicators such as the coefficient of determination ( R 2 ), root-mean-square error (RMSE) and mean absolute error (MAE) demonstrated the superiority of the ANN. In order to scale-up a MAE procedure of chokeberries TPC from the laboratory to the industrial scale, the following set of conditions was proposed: an ethanol concentration of 53.6%, the microwave power of 300 W and the extraction time of 5 min corresponded to a TPC yield of 420.1 mg gallic acid equivalents (GAE)/100 g of fresh plant material.