A team of materials and computer scientists from  Sandia National Laboratories and international collaborators used computational approaches to elucidate new high-entropy alloys with attractive hydrogen storage properties and direct laboratory synthesis and validation.

The team spent more than a year creating twelve new alloys, among hundreds that were modeled, demonstrating how machine learning can help accelerate the future of hydrogen energy by making it easier to create hydrogen infrastructure for consumers.

The Sandia team published a paper detailing its approach with researchers from Ångström Laboratory in Sweden and Nottingham University in the United Kingdom.

“There is a rich history in hydrogen storage research and a database of thermodynamic values describing hydrogen interactions with different materials,” said Matthew Witman, a Sandia research team member.


“With that existing database, an assortment of machine-learning and other computational tools, and state-of-the-art experimental capabilities, we assembled an international collaboration group to join forces on this effort. We demonstrated that machine learning techniques could indeed model the physics and chemistry of complex phenomena which occur when hydrogen interacts with metals.”

Data-driven models, once constructed and trained, only take seconds to execute. Therefore, they can rapidly screen new chemical spaces, in this case, six hundred materials that promise hydrogen storage and transmission.

“This was accomplished in only 18 months,” said Mark Allendorf, another Sandia research team member. “Without the machine learning, it could have taken several years. That’s big when you consider that historically it takes something like 20 years to take a material from lab discovery to commercialization.”

The team also found something that they claim could have dramatic implications for small-scale hydrogen generation at hydrogen fuel-cell filling stations.

“These high-entropy alloy hydrides could enable a natural cascade compression of hydrogen as it moves through the different materials,” said Sandia research team member Vitalie Stavila. “Compressing hydrogen is traditionally done through a mechanical process.”

Building a storage tank with multiple layers of these different high entropy alloy hydrides could compress hydrogen as it moves through the material. As hydrogen goes through all the layers of differing alloys, hydrogen becomes usable in motors that generate electricity.

Hydrogen produced under atmospheric conditions at sea level has a pressure of about 1 bar. For hydrogen to power a vehicle, it must be pressurized to a much higher level. For example, hydrogen at a fuel-cell charging station must have a pressure of 800 bars or higher to be dispensed as 700 bar hydrogen into fuel-cell hydrogen vehicles.

“As hydrogen moves through those layers, it gets more and more pressurized with no mechanical effort,” Stavila explained. “You could theoretically pump in 1 bar of hydrogen and get 800 bar out — the pressure needed for hydrogen charging stations.”

The team is still refining the model but, since the database is already public through the Department of Energy, once the method is better understood, machine learning could lead to breakthroughs in a myriad of fields, including materials science.

Researchers at Sandia National Laboratories recently designed a new class of molten sodium batteries that could improve grid-scale energy storage.

According to recent research supported by the MIT Energy Initiative, hydrogen-fired power generation can be a cost-effective alternative to backing up solar and wind power.