Lithium has been paid great attention in recent years thanks to its significant applications for battery and lightweight alloy. Developing a potential model with high accuracy and efficiency is important for theoretical simulation of lithium materials. Here, we build a deep learning potential (DP) for elemental lithium based on a concurrent-learning scheme and DP representation of the density-functional theory (DFT) potential energy surface (PES), the DP model enables material simulations with close-to DFT accuracy but at much lower computational cost. The simulations show that basic parameters, equation of states, elasticity, defects and surface are consistent with the first principles results. More notably, the liquid radial distribution function based on our DP model is found to match well with experiment data. Our results demonstrate that the developed DP model can be used for the simulation of lithium materials.
Skip Nav Destination
Article navigation
October 2023
Research Article|
October 01 2023
Atomistic modeling of lithium materials from deep learning potential with ab initio accuracy
Special Collection:
Virtual Issue on Machine Learning for Computational Chemistry
Haidi Wang;
Haidi Wang
a
School of Physics, Hefei University of Technology
, Hefei 230091, China
Search for other works by this author on:
Tao Li;
Tao Li
a
School of Physics, Hefei University of Technology
, Hefei 230091, China
Search for other works by this author on:
Yufan Yao;
Yufan Yao
b
Hefei National Laboratory for Physical Sciences at the Microscale, University of Science and Technology of China
, Hefei 230026, China
Search for other works by this author on:
Xiaofeng Liu;
Xiaofeng Liu
a
School of Physics, Hefei University of Technology
, Hefei 230091, China
Search for other works by this author on:
Weiduo Zhu;
Weiduo Zhu
a
School of Physics, Hefei University of Technology
, Hefei 230091, China
Search for other works by this author on:
Zhao Chen;
Zhao Chen
a
School of Physics, Hefei University of Technology
, Hefei 230091, China
Search for other works by this author on:
Zhongjun Li;
Zhongjun Li
*
a
School of Physics, Hefei University of Technology
, Hefei 230091, China
Search for other works by this author on:
Chin. J. Chem. Phys. 36, 573–581 (2023)
Article history
Received:
November 30 2022
Accepted:
December 20 2022
Citation
Haidi Wang, Tao Li, Yufan Yao, Xiaofeng Liu, Weiduo Zhu, Zhao Chen, Zhongjun Li, Wei Hu; Atomistic modeling of lithium materials from deep learning potential with ab initio accuracy. Chin. J. Chem. Phys. 1 October 2023; 36 (5): 573–581. https://doi.org/10.1063/1674-0068/cjcp2211173
Download citation file:
Sign in
Don't already have an account? Register
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Pay-Per-View Access
$40.00
Citing articles via
Ultrafast intrinsic excited state localization m 2D layered As2S3 by interlayer bond formation
Xufeng Li, Li Yao, et al.
Ultrafast proton coupled electron transfer between tryptophan and tyrosine in peptides Trp-Pron-Tyr
Haoyang Li, Simin Cao, et al.
Related Content
Structural and electrocatalytic properties of copper clusters: A study via deep learning and first principles
J. Chem. Phys. (August 2022)
The role of thermal sensitivity of fluid properties, centrifugal destabilization, and nonlinear disturbances on the viscous heating instability in Newtonian Taylor–Couette flow
Physics of Fluids (November 2002)
Lightweight and effective tensor sensitivity for atomistic neural networks
J. Chem. Phys. (May 2023)