This work aims at applying an artificial neural network-group contribution method to represent/predict the surface tension of pure chemical compounds at different temperatures and atmospheric pressure. To propose a comprehensive, reliable, and predictive tool, about 4700 data belonging to experimental surface tension values of 752 chemical compounds at different temperatures and atmospheric pressure have been studied. The investigated compounds belong to 78 chemical families containing 151 functional groups (group contributions), which include organic and inorganic liquids. Using this dedicated strategy, we obtain satisfactory results quantified by the following statistical parameters: absolute average deviations of the represented/predicted properties from existing experimental values, 1.7 %, and squared correlation coefficient, 0.997.