Hydrogen (H 2 ) energy is a promising transition pathway from conventional fossil fuels to sustainable clean energy. However, H 2 requires a large storage capacity because of its low volumetric energy−density nature. Underground H 2 storage sites provide ample space for H 2 storage. In this work, we proposed a general workflow to select saline aquifers' optimal H 2 storage sites, considering the capacity and operational efficiency. We developed a comprehensive data set of high-fidelity numerical simulations to quantify the effects of geologic and operating parameters on H 2 storage performance. The simulation results are used to train a robust reduced-order model (ROM) to estimate H 2 storage performance. Due to its high accuracy and flexibility, we selected the multilayer perceptron to develop our ROM. The mean squared errors of all ROMs are less than 0.0001, and the coefficients of determination (R 2 ) were higher than 0.99. Integrating the performance estimations from the ROMs with volumetric calculations of H 2 storage capacity, we quantitatively evaluated the H 2 storage in saline aquifers using a designed objective function. We applied our workflow in the Intermountain-West (I-WEST) region, which is the central mountain area in the United States, including Arizona, Colorado, New Mexico, Montana, Utah, and Wyoming. We identified the top three promising saline aquifers for H 2 storage from 12 potential storage sites. Our workflow and ROMs are agnostic to the region and could be applied to other areas. Generally, this work supports safe and efficient H 2 storage operations in saline aquifers in the I-WEST region.