The training and test datasets for each elemental metal were generated as follows. First, we fully optimized the atomic positions and lattice constants of 86 prototype structures using the DFT calculation. They comprise single elements with the zero oxidation state from the Inorganic Crystal Structure Database (ICSD), including metallic closed-packed structures, covalent structures, layered structures, and structures reported as high pressure phases. Then, 13000–15000 structures were generated from the optimized prototype structures, and they were randomly divided into training and test datasets at a ratio of nine to one. Each structure was constructed by randomly introducing lattice expansions, lattice distortions, and atomic displacements into a supercell of an optimized prototype structure. No structural data in liquid states, such as structural trajectories in MD simulations at high temperatures, were used to develop the polynomial MLPs.
File details
No response
Method
No response
Method (other)
No response
Software
None
Software (other)
No response
Software version(s)
No response
Additional details
No response
Property types
No response
Other/additional property
No response
Property details
No response
Elements
No response
Number of Configurations
No response
Naming convention
No response
Configuration sets
No response
Configuration labels
No response
Distribution license
No response
Permissions
[ ] I confirm that I have the necessary permissions to submit this dataset
Name
Josh Vita
Email
vita1@llnl.gov
Dataset name
liquids_polynomial_MLP
Authors
Hayato Wakai, Atsuto Seko, Hirosato Izuta, Takayuki Nishiyama, Isao Tanaka
Publication link
https://arxiv.org/abs/2401.14877 since published under: https://doi.org/10.1103/PhysRevB.109.214207
Data link
No response
Additional links
No response
Dataset description
The training and test datasets for each elemental metal were generated as follows. First, we fully optimized the atomic positions and lattice constants of 86 prototype structures using the DFT calculation. They comprise single elements with the zero oxidation state from the Inorganic Crystal Structure Database (ICSD), including metallic closed-packed structures, covalent structures, layered structures, and structures reported as high pressure phases. Then, 13000–15000 structures were generated from the optimized prototype structures, and they were randomly divided into training and test datasets at a ratio of nine to one. Each structure was constructed by randomly introducing lattice expansions, lattice distortions, and atomic displacements into a supercell of an optimized prototype structure. No structural data in liquid states, such as structural trajectories in MD simulations at high temperatures, were used to develop the polynomial MLPs.
File details
No response
Method
No response
Method (other)
No response
Software
None
Software (other)
No response
Software version(s)
No response
Additional details
No response
Property types
No response
Other/additional property
No response
Property details
No response
Elements
No response
Number of Configurations
No response
Naming convention
No response
Configuration sets
No response
Configuration labels
No response
Distribution license
No response
Permissions