Interpretable AI reveals key atomic traits for efficient hydrogen storage in metal hydrides

Hydrogen fuels represent a clean energy option, but a major hurdle in making its use more mainstream is efficient storage. Hydrogen storage requires either extremely high-pressure tanks or extremely cold temperatures, which means that storage alone consumes a lot of energy. This is why metal hydrides, which can store hydrogen more efficiently, are such a promising option.

New digital platform advances hydrogen research

To help accurately predict performance metrics of hydrogen storage materials, researchers at Tohoku University used a newly established data infrastructure: the Digital Hydrogen Platform (DigHyd). DigHyd integrates more than 5,000 meticulously curated experimental records from the literature, supported by an AI language model. The work is published in the journal Chemical Science.

Leveraging this extensive database, researchers systematically explored physically interpretable models and found that fundamental atomic features—atomic mass, electronegativity, molar density, and ionic filling factor—emerge as key descriptors. Other researchers can use this as a tool for guiding their materials design process, without having to go through a lengthy trial-and-error process in the lab to search for potential candidates.

“Not only does this white-box regression model make accurate predictions, but it maintains full physical interpretability,” explains Hao Li, Distinguished Professor of the Advanced Institute for Materials Research (WPI-AIMR), Tohoku University. “This means that it is transparent, unlike conventional ‘black-box’ machine learning approaches where it is unclear how the model calculated its final answer.”

This transparency allows scientists to identify design strategies, since the model shows mathematically simple, yet clearly interpretable expressions for the target metrics. By correlating fundamental atomic-scale properties with measurable storage behavior, the models provide a clear and chemically intuitive picture of how material composition governs hydrogen absorption and release.

Key findings and future directions

The study also uncovered a fundamental trade-off that defines the current landscape of metal hydrides. Compounds made of light, electropositive elements exhibit high hydrogen capacities but yield low equilibrium pressure at room temperature, while those based on heavier transition metals release hydrogen more readily but at the expense of capacity. Remarkably, beryllium-based alloys emerged as unique systems capable of balancing these conflicting characteristics, combining both high storage density and suitable thermodynamic stability.

Beyond identifying promising candidates, this work establishes a methodology for accelerating discovery in energy materials research. The descriptor-based framework offers a new paradigm for connecting data-driven analysis with physical understanding, providing a scalable and transparent foundation for the design of hydrogen storage materials.

This approach can be extended to more complex alloys and porous structures, offering a path toward the development of safe, efficient, and high-capacity hydrogen storage systems that will support the transition to clean, carbon-neutral energy technologies.