Efficient Training of the Machine-Learning Interatomic Potential Based on an Artificial Neural Network for Estimating the Helmholtz Free Energy of Alkali Metals-Reference-Cited by-同舟云学术

Efficient Training of the Machine-Learning Interatomic Potential Based on an Artificial Neural Network for Estimating the Helmholtz Free Energy of Alkali Metals

Published:2023-05-15 Issue:5 Volume:92 Page:
ISSN:0031-9015
Container-title:Journal of the Physical Society of Japan
language:en
Short-container-title:J. Phys. Soc. Jpn.

Author:

Fukushima Shogo¹^ORCID,Shimamura Kohei¹^ORCID,Koura Akihide¹^ORCID,Shimojo Fuyuki¹^ORCID

Affiliation:

1. Department of Physics, Kumamoto University, Kumamoto 860-8555, Japan

Funder

Core Research for Evolutional Science and Technology

Japan Society for the Promotion of Science

Publisher

Physical Society of Japan

Subject

General Physics and Astronomy

Link

https://journals.jps.jp/doi/pdf/10.7566/JPSJ.92.054005

Reference22 articles.

1. Efficient approach to compute melting properties fully from ab initio with application to Cu

2. Melting properties from ab initio free energy calculations: Iron at the Earth's inner-core boundary

3. High-pressure phase diagram of beryllium from ab initio free-energy calculations

4. Ab Initio Atomistic Simulations of Ca‐Perovskite Melting

5. Thermodynamic integration by neural network potentials based on first-principles dynamic calculations

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Thermal conductivity calculation using homogeneous non-equilibrium molecular dynamics simulation with Allegro;International Journal of Heat and Mass Transfer;2024-12

2. Thermal Conductivity Calculation Using Homogeneous Non-Equilibrium Molecular Dynamics Simulation with Allegro;2024