Hydrogen Adsorption Isotherms in Zeolites
Due to its low energy density, hydrogen must be stored in a compressed or cryogenic state. Adsorption-based storage technologies represent a promising alternative, as they can reduce compression costs when achieving higher energy densities than conventional storage methods. Nanoporous zeolites stand out as highly promising materials for H₂ storage at room temperature.
To investigate this potential, we performed Monte Carlo simulations in the grand canonical ensemble, obtaining H₂ adsorption isotherms at 298 K up to 350 bar for different samples from the IZA Database of Zeolite Structures. This dataset was then used to train machine learning models aimed at predicting the storage capacity of other zeolite structures not directly simulated.
Among the algorithms evaluated, XGBoost showed the best performance (R² = 0.993) in predicting H₂ adsorption isotherms. To broaden access to these results, we provide the following resources for download:
These resources enable researchers and engineers to replicate the results and directly integrate the models into their studies and applications related to the development of hydrogen storage technologies.