Skip to content

how much initial random data do I need to prepare to be more suitable #1230

Description

@XuFanffei

I am currently working on the dp potential field of a high entropy alloy with six fixed components. Using an initial dataset of 128 initial random crystal cells, each with 128 atoms, a total of over 1300 initial data pieces were processed through ten steps of AIMD. Contains random lattice constants with random configurations such as fcc, bcc, hcp, etc. Throw it into the dpgen and run, but it turns out that no reasonable configuration can be explored. I would like to ask if the initial dataset is too small. If it is a six element alloy with an unknown configuration, how much initial random data do I need to prepare to be more suitable

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    questionFurther information is requested

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions