Abstract
An open question in the metal hydride community is whether there are simple, physics-based design rules that dictate the thermodynamic properties of these materials across the variety of structures and chemistry they can exhibit. While black box machine learning-based algorithms can predict these properties with some success, they do not directly provide the basis on which these predictions are made, therefore complicating the a priori design of novel materials exhibiting a desired property value. In this work we demonstrate how feature importance, as identified by a gradient boosting tree regressor, uncovers the strong dependence of the metal hydride equilibrium H2 pressure on a volume-based descriptor that can be computed from just the elemental composition of the intermetallic alloy. Elucidation of this simple structure-property relationship is valid across a range of compositions, metal substitutions, and structural classes exhibited by intermetallic hydrides. This permits rational targeting of novel intermetallics for high-pressure hydrogen storage (low-stability hydrides) by their descriptor values, and we predict a known intermetallic to form a low-stability hydride (as confirmed by density functional theory calculations) that has not yet been experimentally investigated.
Highlights
Development of renewable energy technologies is more critical than ever to avoid some of the catastrophic consequences of climate change.[1]
An open question is whether there exist simple materials design rules that dictate their thermodynamic properties across their varying chemical and structural space
Hattrick-Simpers et al trained a model on the Department of Energy’s experimental metal hydride (HydPARK) database to predict hydriding enthalpies solely from the composition of the intermetallic phase, which was used as a surrogate model to quickly evaluate the performance of novel intermetallic compositions for use in hydrogen compressors.[47]
Summary
Development of renewable energy technologies is more critical than ever to avoid some of the catastrophic consequences of climate change.[1]. In this work we train an ML model on the HydPARK database using features derived solely from the intermetallic composition (no structural or hydride information); our major contribution is to use feature importance from gradient boosting trees to gain “explainable” insight into simple structure-property relationships that govern the thermodynamics of hydride formation. While our ML model can accurately predict the room temperature equilibrium H2 pressure of intermetallic hydrides, its interpretability allows us to generalize the pressure dependence on the lattice volume in the LaNi5 substitution series (a historically known design correlation18–20) over a surprisingly wide range of intermetallic chemistries and structures This unifies disparate experimental results onto a single structure-property relationship. The data of Smith et al.[17] in Figure 3 corresponds to the “miscellaneous” hydride class R6Fe23 [R=Ho,Er,Lu], whereby rare earth substitution expands νpa and leads to an (b) 5
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
