The common technique to extract plant ingredients is the conventional method such as Soxhlet with organic solvents that is time-consuming and consumes a large amount of solvent and damages thermo-sensitive substances for use of high temperature. But for pharmaceutical and medicinal applictions, a suitable method for extraction and purification without utilization of toxic organic solvents is needed. Supercritical fluid extraction especially supercritical carbon dioxide extraction as an efficient extraction method has attracted attention during the last decades, as its advantages include being non-explosive, non-toxic, and available in high purity with low cost, non-solvent residues. Research has shown that synthetic antioxidants have carcinogenic properties so natural antioxidants have received much more attention in recent years for health reasons especially in plant sources. A valuable resource for human health, is sunflower seed that is rich in minerals, antioxidants and vitamins. It contains phenols, which are the most powerful antioxidant and has applications in the medical, industrial. Phenolic acids have anti-tumor, anti-bacterial, anti-inflammatory, antipyretic, anti-fungal and anti-pain because of their antioxidant effect .polyphenol compounds found in sunflower is chlorogenic acid which is a natural antioxidant and acts as an anti-diabetic, anti blood pressure and the prevention of diseases such as cancer ,coronary heart disease, and osteoporosis as well. In this study, the extraction of CGA from sunflowerseed was investigated by modified supercritical CO 2 and Soxhlet extraction with constant volume of co-solvent (2 ml), 25 min of static time and 0.6 mm of average particle size. Design of experiment carried out with response surface methodology (RSM) using Mini Tab software. The operating temperature (40-80) by step 10°C), the operating pressure (10-30 by step 5 Mpa), the dynamic extraction time (40-120 by step 20 min), and the flow rate of CO2 (0.6-1.8 by step 0.3 ml/min) have been considered as operating variables. Response surface analysis verified that the data were adequately fitted to second-order polynomial model. The linear and quadratics terms of temperature, pressure, CO 2 flow rate, and dynamic time, as well as the interaction between pressure-temperature had significant effects on the proposed model of CGA recovery based on coded variables. R 2 and modified R 2 of the model are 96.76% and 93.91%, respectively. It was predicted that the optimum extraction conditions within the experimental ranges would be the extraction pressure of 17.00 MPa, temperature of 40.1, flow rate of 1.6 ml/min, and extraction time of 104.60min with recovery of 52.08. Moreover, in the present study, two mathematical modeling shrinking core and broken and intact cell for CGA extraction from sunflower seed was performed by modified supercritical carbon dioxide based on Density and viscosity of dense gases mixture was obtained by Peng-Robion (PR) equation of state with the van der Waals mixing rules and Chung et al., respectively. 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 thermodynamic modeling of solubilities. Indicated by obtained results, the mathematical model is able to predict the experimental data with acceptable accuracy and R 2 is 95%. 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 40.1 ?C, 17.8 MPa, 1.54 ml/min, and 112.483 min (dynamic time) to achieve 51.28 recovery. There was good agreement between two methods of optimization (genetic and RSM). Finally, neural network modeling was done by one hidden layer with 10 neuron, respectively. The results showed the truly trained network and very good compatibility between the neural networks and experimental data for recovery. Key Words Chlorogenic acid, Supercritical extraction, Co-solvent, Response surface methodology, Mathematical modeling, Genetic algorithm, Neural network.