The effective CO2 sequestration in saline aquifers as a climate change-lessening solution is mainly governed by the interfacial tension (IFT) behavior between CO2 and brine. An innovative and competent decision tree-based approach called stochastic gradient boosting (SGB) tree algorithm was applied to predict the CO2-aquifer brine IFT as a function of temperature, pressure, and brine salinities. The produced results were compared with the previously reported outcomes of other machine learning models, namely, radial basis function networks, multilayer perceptron networks, least squares support vector machine, and adaptive neuro fuzzy inference system. Amongst all models, the developed SGB tree algorithm provided superior outputs and turned out to be the most accurate tool.