Principal component analysis enables the design of deep learning potential precisely capturing LLZO phase transitions
Open Access
- 18 March 2024
- journal article
- research article
- Published by Springer Nature in npj Computational Materials
- Vol. 10 (1) , 1-9
Abstract
The development of accurate and efficient interatomic potentials using machine learning has emerged as an important approach in materials simulations and discovery. However, the systematic construction of diverse, converged training sets remains challenging. We develop a deep learning-based interatomic potential for the Li7La3Zr2O12 (LLZO) system. Our interatomic potential is trained using a diverse dataset obtained from databases and first-principles simulations. We propose using the coverage of the training and test sets as the convergence criteria for the training iterations, where the coverage is calculated by principal component analysis. This results in an accurate LLZO interatomic potential that can describe the structure and dynamical properties of LLZO systems meanwhile greatly reducing computational costs compared to density functional theory calculations. The interatomic potential accurately describes radial distribution functions and thermal expansion coefficient consistent with experiments. It also predicts the tetragonal-to-cubic phase transition behaviors of LLZO systems. Our work provides an efficient training strategy to develop accurate deep-learning interatomic potential for complex solid-state electrolyte materials, providing a promising simulation tool to accelerate solid-state battery design and applications.Keywords
Funding Information
- National Natural Science Foundation of China (11874307)
This publication has 42 references indexed in Scilit:
- DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamicsComputer Physics Communications, 2018
- Challenges and perspectives of garnet solid electrolytes for all solid-state lithium batteriesJournal of Power Sources, 2018
- Lithium garnets: Synthesis, structure, Li + conductivity, Li + dynamics and applicationsProgress in Materials Science, 2017
- Intergranular Li metal propagation through polycrystalline Li6.25Al0.25La3Zr2O12 ceramic electrolyteElectrochimica Acta, 2017
- Potential of lithium-ion batteries in renewable energyRenewable Energy, 2015
- Influence of lithium oxide additives on densification and ionic conductivity of garnet-type Li6.75La3Zr1.75Ta0.25O12 solid electrolytesSolid State Ionics, 2013
- Electrochemical performance of an all-solid-state lithium ion battery with garnet-type oxide electrolyteJournal of Power Sources, 2012
- Principal component analysisWIREs Computational Statistics, 2010
- Li6ALa2Ta2O12 (A = Sr, Ba): Novel Garnet‐Like Oxides for Fast Lithium Ion ConductionAdvanced Functional Materials, 2005
- Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis setComputational Materials Science, 1996