Researchers from Sandia National Laboratories and international collaborators used computational approaches, including explainable machine learning models, to elucidate new high-entropy alloys with attractive hydrogen storage properties and direct laboratory synthesis and validation.
Solid-state hydrogen storage materials that are optimized for specific use cases could be a crucial facilitator of the hydrogen economy transition. Yet, the discovery of novel hydriding materials has historically been a manual process driven by chemical intuition or experimental trial and error. Data-driven materials’ discovery paradigms provide an alternative to traditional approaches, whereby machine/statistical learning (ML) models are used to efficiently screen materials for desired properties and significantly narrow the scope of expensive/time-consuming first-principles modeling and experimental validation.
Here, we specifically focus on a relatively new class of hydrogen storage materials, high entropy alloy (HEA) hydrides, whose vast combinatorial composition space and local structural disorder necessitate a data-driven approach that does not rely on exact crystal structures to make property predictions. Our ML model quickly screens hydride stability within a large HEA space and permits down selection for laboratory validation based on not only targeted thermodynamic properties but also secondary criteria such as alloy phase stability and density.
Witman et al.
Vitalie Stavila, Mark Allendorf, Matthew Witman and Sapan Agarwal are part of the Sandia team that published a paper in conjunction with researchers from Ångström Laboratory in Sweden and Nottingham University in the United Kingdom in the ACS journal Chemistry of Materials detailing the approach.
There is a rich history in hydrogen storage research and a database of thermodynamic values describing hydrogen interactions with different materials. 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.
Having a data-driven modeling capability to predict thermodynamic properties can rapidly increase the speed of research. Once constructed and trained, such machine learning models only take seconds to execute and can therefore rapidly screen new chemical spaces: in this case 600 materials that show promise for hydrogen storage and transmission.
This was accomplished in only 18 months. 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 that these high-entropy alloy hydrides could enable a natural cascade compression of hydrogen as it moves through the different materials, said Stavila. Compressing hydrogen is traditionally done through a mechanical process. This finding could have significant implications for small-scale hydrogen generation at hydrogen fuel-cell filling stations.
Hydrogen produced under atmospheric conditions at sea level has a pressure of about 1 bar. Hydrogen at a fuel-cell charging station must have a pressure of 800 bars or higher so that it can be dispensed as 700-bar hydrogen into fuel-cell hydrogen vehicles.
Stavila described building a storage tank with multiple layers of these different alloys. As hydrogen is pumped into the tank, the first layer compresses the gas as it moves through the material. The second layer compresses it even further and so on through all of the layers of differing alloys.
As hydrogen moves through those layers, it gets more and more pressurized with no mechanical effort. 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, using machine learning could lead to breakthroughs in a myriad of fields, including materials science, Agarwal said.
This research was sponsored by the Hydrogen and Fuel Cell Technologies Office within the US Department of Energy, Office of Energy Efficiency and Renewable Energy and through Sandia’s Laboratory Directed Research and Development program.
Matthew Witman, Gustav Ek, Sanliang Ling, Jeffery Chames, Sapan Agarwal, Justin Wong, Mark D. Allendorf, Martin Sahlberg, and Vitalie Stavila (2021) “Data-Driven Discovery and Synthesis of High Entropy Alloy Hydrides with Targeted Thermodynamic Stability” Chemistry of Materials 33 (11), 4067-4076 doi: 10.1021/acs.chemmater.1c00647