Data

Tools

Indexes

Applications

Experiments

Open Source Science

lasp2interface

Interface for on-the-fly training of Machine Learning Interaction Potentials

https://github.com/lam-group/lasp2interface

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.3%) to scientific vocabulary

Keywords

lammps machine-learning materials-science n2p2 physics simulation vasp
Last synced: 4 months ago · JSON representation ·

Repository

Interface for on-the-fly training of Machine Learning Interaction Potentials

Basic Info
Statistics
  • Stars: 2
  • Watchers: 1
  • Forks: 1
  • Open Issues: 0
  • Releases: 1
Topics
lammps machine-learning materials-science n2p2 physics simulation vasp
Created over 3 years ago · Last pushed over 1 year ago
Metadata Files
Readme Citation

README.md

LASP2 Interface

This repository provides an interface for 'on the flight' training of a high dimensional neural network. This software is an interface between three programs (n2p2, LAMMPS, and VASP). The LAMMPS software is used for the dynamics of the simulation, using a potential created with the n2p2 software for high dimensional neural network potentials. VASP is the reference method with which the potentials are trained.

Basic usage

LASP2 requires as input configuration files for n2p2, LAMMPS and VASP, as well as a own LASP2 configuration file. The n2p2 input that is required consists of: - The n2p2Input directory containing subdirectories for each of the different seeds used. The subdirectories must contain the input.nn and input.data files used for training. - The PotentialsComplete directory contanining subdirectories for each of the different seeds used. The subdirectories must contain the files necessary to load an hdnnp potential in LAMMPS. - A completeinput.data file with the complete database used for training.

For LAMMPS, the required input consists of: - An input file named input.lmp containing the commands to run the desired simulation. - A second input file named restart.lmp with instructions that need to be defined again after restarting the simulation. The simulation will stop when training is needed, and it will be restarted after the neural network potential is trained again. - The structure used as starting point for the simulation.

In order to use VASP, the interface requires the following input files: - A directory named vaspInput containing the INCAR, KPOINTS, and POTCAR files, as well as a copy of the VASP binary.

Output

When the simulation is finished, the interface will produce a plot of the dispersion between the potentials with different random seeds as a function of the steps of the simulation. The output of the VASP calculations will be stored in a directory named DFT, numbered by the number of computations made throughout the computation. Similarly, the output of n2p2 training can be found in the directory named Training, containing subdirectories for the short and long trainings numbered also by the number of trainings performed throughout the simulation. The last potentials used in the simulation can be found in a subdirectory named Potentials under the Training directory.

Owner

  • Name: lamGroup
  • Login: LAM-GROUP
  • Kind: user

Materials modelling group

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Salazar Letona"
  given-names: "Carlos Rafael"
  orcid: "https://orcid.org/0000-0002-3126-2033"
title: "LASP2Interface"
version: 1.0.0
doi: 10.5281/zenodo.7592253
date-released: 2023-01-31
url: "https://lasp2interface.readthedocs.io/"

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1

Committers

Last synced: almost 2 years ago

All Time
  • Total Commits: 132
  • Total Committers: 1
  • Avg Commits per committer: 132.0
  • Development Distribution Score (DDS): 0.0
Past Year
  • Commits: 12
  • Committers: 1
  • Avg Commits per committer: 12.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
carle13 c****l@h****m 132

Issues and Pull Requests

Last synced: almost 2 years ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

lib/requirements.txt pypi
  • ase *
  • matplotlib *
  • mpi4py ==3.1.3
  • numpy *
  • pyinstaller ==5.1
  • pyinstaller-hooks-contrib ==2022.7
requirements.txt pypi
  • Jinja2 ==3.0.3
  • mkdocs ==1.3.1
  • mkdocs-autorefs ==0.4.1
  • mkdocs-git-revision-date-localized-plugin ==1.1.0
  • mkdocs-material ==8.3.9
  • mkdocs-material-extensions ==1.0.3
  • mkdocstrings ==0.19.0
  • mkdocstrings-python ==0.7.1