The success of geological H2 storage relies significantly on rock–H2–brine interactions and wettability. Experimentally assessing the H2 wettability of storage/caprocks as a function of thermos-physical conditions is arduous because of high H2 reactivity and embrittlement damages. Data-driven machine learning (ML) modeling predictions of rock–H2–brine wettability are less strenuous and more precise. They can be conducted at geo-storage conditions that are impossible or hazardous to attain in the laboratory. Thus, ML models were utilized in this research to accurately model the wettability behavior of a ternary system consisting of H2, rock minerals (quartz and mica), and brine at different operating geological conditions. The results revealed that the ML models accurately captured the wettability behavior at different geo-storage conditions by yielding less than 5% mean absolute percent error and above 0.95 coefficient of determination values. The partial dependency or sensitivity plots were generated to evaluate the impact of individual features on the trained models. These plots revealed that the models accurately captured the physics behind the problem. Furthermore, a mathematical equation is derived from the trained ML model to predict the wettability behavior without using any ML software. The accuracy of the predictions of the ML model can be beneficial for exactly predicting the H2 geo-storage capacities and assessing of H2 containment security of storage and caprocks for large-scale geo-storage projects.