Recently, scientists have proven the licorice therapeutic effects on various diseases, such as, cancer, diabetes, kidney stones, inflammation, ulcers, skin diseases, tuberculosis, viral diseases, respiratory diseases, liver etc. by extensive researches. Licorice is composed of various compounds. Most of its antioxidant effects are often attributed to glycyrrhizic acid (GA). Therefore, necessity of GA extraction and producing extract of antioxidant is obvious. In this study, the extraction of GA from licorice plant root was investigated by Soxhlet and modified supercritical CO 2 extraction with different volume ratios of water and methanol as modifier, 30 min of static time and 0.674 mm of average particle size. Design of experiment carried out with response surface methodology (RSM) using Minitab 17 software. The operating temperature (45-65), the operating pressure (10-34), the dynamic extraction time (40-120), the flow rate of CO 2 (0.8-2) and methanol concentration in methanol-water binary entrainer (0-100%) have been considered as operating variables. Response surface analysis verified that the data were adequately fitted to second-order polynomial model. The linear terms of temperature, pressure, CO 2 flow rate, co-solvent methanol concentration and dynamic time as well as quadratic terms of all variables except CO 2 flow rate had significant effects on the obtained RSM model of GA recovery based on coded variables. R2 and modified R2 of the model are 98.05% and 94.51%, respectively. The maximum GA recovery of 54.4% was predicted by the RSM model at the optimal operating conditions of 29.6 MPa, 68 o C, 108 min (dynamic time), 2 ml/min and 46.5% methanol concentration in binary modifier. Moreover, in the present study, a mathematical modeling for GA extraction from licorice plant root was performed by modified supercritical carbon dioxide based on the differential mass balance. Mathematical model parameters are including effective pore diffusivity, film mass transfer coefficient, axial dispersion, and distribution coefficient. The first three parameters were obtained from empirical equations and the distribution coefficient between solid and solvent has been determined by applying the genetic algorithm to minimize the average absolute deviation (AAD) between the data obtained from experiments and model equations. In addition, RSM was used to determine the effects of temperature and pressure on the solubility (S) of GA in the supercritical fluid and co-solvent so that we can use the obtained formula for Kp to put it in the mathematical model and finally determine the optimum operating conditions. The main process conditions which must be determined to maximize the extraction recovery are temperature, pressure, flow rate of CO 2 , and dynamic extraction time. These were optimized by genetic algorithm. The optimal operating conditions were observed at 68 ?C, 27.19 MPa, 1.96 ml/min, and 119 min (dynamic time) to achieve 0.338 recovery. A three-layer artificial neural network was also developed for modeling of GA extraction from licorice plant root. In this regard, different networks (by changing the number of neurons in the hidden layer and algorithm of network training) were compared with evaluation of networks accuracy in extraction recovery prediction. One-step secant back propagation algorithm with six neurons in hidden layer was found to be the most suitable network and the coefficient of determination (R 2 ) was 98.5% Key Words Glycyrrhizic acid, Supercritical extraction, Co-solvent, Response surface methodology, Mathematical modeling, Genetic algorithm, Neural network.