Nowadays artificial neural networks(ANNs) with strong ability have been applied widely for prediction of nonlinear phenomenon. In this work an optimized ANN with 7 inputs that consist of temperature, pressure, critical temperature, critical pressure, density, molecular weight and acentric factor has been used for solubility prediction of three disperse dyes in supercritical carbon dioxide(SC-CO2) and ethanol as co-solvent. It was shown how a multi-layer perceptron network can be trained to represent the solubility of disperse dyes in SC-CO2. Numeric Sensitivity Analysis and Garson equation were utilized to find out the degree of effectiveness of different input variables on the efficiency of the proposed model. Results showed that our proposed ANN model has correlation coefficient, Nash–Sutcliffe model efficiency coefficient and discrepancy ratio about 0.998, 0.992, and 1.053 respectively. Nowadays artificial neural networks (ANNs) with strong ability have been applied widely for prediction of nonlinear phenomenon. In this work an optimized ANN with 7 inputs that consist of temperature, pressure, critical temperature, critical pressure, density, molecular weight and acentric factor has was used for solubility prediction of three disperse dyes in supercritical carbon dioxide (SC-CO2) and ethanol as co-solvent. It was illustrated how a multi-layer perceptron network can be trained to represent the solubility of disperse dyes in SC-CO2. Numeric Sensitivity Analysis and Garson equation were utilized to find out the degree of effectiveness of different input variables on the efficiency of the proposed model. Results showed that our proposed ANN model has correlation coefficient, Nash-Sutcliffe model efficiency coefficient and discrepancy ratio of about 0.998, 0.992, and 1.053 respectively.