In a collaborative effort, researchers from the University of Wisconsin-Madison, Ames Laboratory, and the University of North Texas have leveraged machine learning to accelerate the discovery of new hydrogen storage materials, a critical component in the transition to a low-carbon economy.
The team, led by Dr. Ganesh Balasubramanian and Dr. Prashant Singh, focused on metal hydrides, which are known for their hydrogen-storage capacity. They employed machine learning (ML) models to predict hydrogen-to-metal (H/M) ratios and solution energy by incorporating thermodynamic parameters and local lattice distortion (LLD) as key features. Their best-performing model, a Gradient Boosting Regression model, provided improved predictions for a broad class of ternary alloys, such as Ti-Nb-X and Co-Ni-X, which can be easily extended to multi-principal-element alloys.
The researchers found that certain elements, like Ti, Nb, and V, enhance hydrogen storage capacity, while others, like Mo, reduce it by 40-50%. They attributed this to slow hydrogen kinetics in molybdenum-rich alloys, which was validated by pressure-composition isotherm (PCT) experiments on pure Ti and Ti5Mo95 alloys. Density functional theory (DFT) and molecular simulations further confirmed that Ti and Nb promote hydrogen diffusion, whereas Mo hinders it. This highlights the interplay between electronic structure, lattice distortions, and hydrogen uptake.
To aid material selection, the team presented two periodic tables illustrating elemental effects on hydrogen weight percent and solution energy, derived from ML. These tables serve as a reference for identifying alloying elements that enhance hydrogen solubility and storage. The research was published in the journal Nature Communications.
This study demonstrates the potential of machine learning in accelerating materials discovery for hydrogen storage, a key technology for enabling a low-carbon energy future. By providing a data-driven approach to identifying promising materials, this research could help the energy sector develop more efficient and sustainable energy-storage solutions.
This article is based on research available at arXiv.