Hydrogen diffusion in metals and alloys plays an important role in the discovery of new materials for fuel cell and energy storage technology. While analytic models use hand-selected features that have clear physical ties to hydrogen diffusion, they often lack accuracy when making quantitative predictions. Machine learning models are capable of making accurate predictions, but their inner workings are obscured, rendering it unclear which physical features are truly important. To develop interpretable machine learning models to predict the activation energies of hydrogen diffusion in metals and random binary alloys, we create a database for physical and chemical properties of the species and use it to fit six machine learning models. Our models achieve root-mean-squared errors between 98–119 meV on the testing data and accurately predict that elemental Ru has a large activation energy, while elemental Cr and Fe have small activation energies. By analyzing the feature importances of these fitted models, we identify relevant physical properties for predicting hydrogen diffusivity. While metrics for measuring the individual feature importances for machine learning models exist, correlations between the features lead to disagreement between models and limit the conclusions that can be drawn. Instead grouped feature importance, formed by combining the features via their correlations, agree across the six models and reveal that the two groups containing the packing factor and electronic specific heat are particularly significant for predicting hydrogen diffusion in metals and random binary alloys. In conclusion, this framework allows us to interpret machine learning models and enables rapid screening of new materials with the desired rates of hydrogen diffusion.
Lu, Grace M., et al. "Explainable machine learning for hydrogen diffusion in metals and random binary alloys." Physical Review Materials, vol. 7, no. 10, Oct. 2023. https://doi.org/10.1103/physrevmaterials.7.105402
Lu, Grace M., Witman, Matthew, Agarwal, Sapan, et al., "Explainable machine learning for hydrogen diffusion in metals and random binary alloys," Physical Review Materials 7, no. 10 (2023), https://doi.org/10.1103/physrevmaterials.7.105402
@article{osti_2311334,
author = {Lu, Grace M. and Witman, Matthew and Agarwal, Sapan and Stavila, Vitalie and Trinkle, Dallas R.},
title = {Explainable machine learning for hydrogen diffusion in metals and random binary alloys},
annote = {Hydrogen diffusion in metals and alloys plays an important role in the discovery of new materials for fuel cell and energy storage technology. While analytic models use hand-selected features that have clear physical ties to hydrogen diffusion, they often lack accuracy when making quantitative predictions. Machine learning models are capable of making accurate predictions, but their inner workings are obscured, rendering it unclear which physical features are truly important. To develop interpretable machine learning models to predict the activation energies of hydrogen diffusion in metals and random binary alloys, we create a database for physical and chemical properties of the species and use it to fit six machine learning models. Our models achieve root-mean-squared errors between 98–119 meV on the testing data and accurately predict that elemental Ru has a large activation energy, while elemental Cr and Fe have small activation energies. By analyzing the feature importances of these fitted models, we identify relevant physical properties for predicting hydrogen diffusivity. While metrics for measuring the individual feature importances for machine learning models exist, correlations between the features lead to disagreement between models and limit the conclusions that can be drawn. Instead grouped feature importance, formed by combining the features via their correlations, agree across the six models and reveal that the two groups containing the packing factor and electronic specific heat are particularly significant for predicting hydrogen diffusion in metals and random binary alloys. In conclusion, this framework allows us to interpret machine learning models and enables rapid screening of new materials with the desired rates of hydrogen diffusion.},
doi = {10.1103/physrevmaterials.7.105402},
url = {https://www.osti.gov/biblio/2311334},
journal = {Physical Review Materials},
issn = {ISSN 2475-9953},
number = {10},
volume = {7},
place = {United States},
publisher = {American Physical Society (APS)},
year = {2023},
month = {10}}
Sandia National Laboratories (SNL-CA), Livermore, CA (United States)
Sponsoring Organization:
National Science Foundation (NSF); USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA)
Züttel, Andreas; Remhof, Arndt; Borgschulte, Andreas
Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 368, Issue 1923https://doi.org/10.1098/rsta.2010.0113
