Project: mlearn (GitHub Link)

mlearn-master
- .circleci
  - config.yml
- requirements-ci.txt
- mlearn
  - data.py
  - models.py
  - describers.py
  - __init__.py
  - tests
    - test_data.py
    - test_describers.py
    - test_models.py
    - datapool.json
    - __init__.py
  - potentials
    - gap.py
    - nnp.py
    - lammps
      - templates
        latt
        in.latt
        efs
        in.efs
        neb
        in.neb
        in.relax
        elastic
        in.elastic
        init.template
        potential.template
        displace.template
        defect
        in.defect
      - calcs.py
      - __init__.py
      - tests
        test_calcs.py
        coeff.json
        __init__.py
    - mtp.py
    - params
      - 08g.mtp
      - GAP.json
      - MTini.json
      - NNinput.json
    - __init__.py
    - tests
      - MTP
        fitted.mtp
      - test_gap.py
      - NNP
        weights.data
        input.nn
        scaling.data
      - SNAP
        SNAPotential.snapparam
        SNAPotential.snapcoeff
      - datapool.json
      - __init__.py
      - test_snap.py
      - test_mtp.py
      - test_nnp.py
    - snap.py
- LICENSE
- notebooks
  - qSNAP_example
    - example.ipynb
    - data.json
    - conventional.cif
    - test_struct.cif
    - SNAPotential.snapparam
    - SNAPotential.snapcoeff
  - NNP_example
    - example.ipynb
    - weights.data
    - data.json
    - input.nn
    - conventional.cif
    - scaling.data
    - test_struct.cif
  - SNAP_example
    - example.ipynb
    - data.json
    - conventional.cif
    - test_struct.cif
    - SNAPotential.snapparam
    - SNAPotential.snapcoeff
  - GAP_example
    - example.ipynb
    - data.json
    - conventional.cif
    - soap.xml
    - test_struct.cif
  - MTP_example
    - example.ipynb
    - data.json
    - conventional.cif
    - README.md
    - test_struct.cif
- setup.py
- data
  - Ni
  - Cu
  - Si
  - Li
  - Ge
  - Mo
- mvl_models
  - Ni
    - snap
      - Ni_conventional.cif
      - SNAPotential.snapparam
      - SNAPotential.snapcoeff
    - gap
      - Ni_conventional.cif
    - qsnap
      - Ni_conventional.cif
      - SNAPotential.snapparam
      - SNAPotential.snapcoeff
    - nnp
      - Ni_conventional.cif
      - input.nn
      - weights.028.data
      - scaling.data
  - Cu
    - snap
      - SNAPotential.snapparam
      - SNAPotential.snapcoeff
    - gap
    - qsnap
      - SNAPotential.snapparam
      - SNAPotential.snapcoeff
    - nnp
      - weights.029.data
      - input.nn
      - scaling.data
  - Si
    - snap
      - SNAPotential.snapparam
      - SNAPotential.snapcoeff
    - gap
    - qsnap
      - SNAPotential.snapparam
      - SNAPotential.snapcoeff
    - nnp
      - weights.014.data
      - input.nn
      - scaling.data
  - README.md
  - Li
    - snap
      - SNAPotential.snapparam
      - SNAPotential.snapcoeff
    - gap
    - qsnap
      - SNAPotential.snapparam
      - SNAPotential.snapcoeff
    - nnp
      - input.nn
      - scaling.data
  - Ge
    - snap
      - SNAPotential.snapparam
      - SNAPotential.snapcoeff
    - gap
    - qsnap
      - SNAPotential.snapparam
      - SNAPotential.snapcoeff
    - nnp
      - input.nn
      - weights.032.data
      - scaling.data
  - Mo
    - snap
      - SNAPotential.snapparam
      - SNAPotential.snapcoeff
    - gap
    - qsnap
      - SNAPotential.snapparam
      - SNAPotential.snapcoeff
    - nnp
      - weights.042.data
      - input.nn
      - scaling.data
- setup.cfg
- README.md
- requirements.txt
- .gitignore
- docs
  - install.md
- MANIFEST.in

mlearn

The mlearn package is a benchmark suite for machine learning interatomic potentials for materials science. It enables a seamless way to develop various potentials and provides LAMMPS-driven properties predictor with developed potentials as plugins.

Installation

The usage of mlearn requires installation of specific packages and the plugins in LAMMPS. Please see detailed installation instructions for all descriptors.

Jupyter Notebook Examples

References

Gaussian Approximation Potential: Bartók, A. P.; Payne, M. C.; Kondor, R.; Csányi, G. Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons. Physical Review Letters 2010, 104, 136403. doi:10.1103/PhysRevLett.104.136403.
Moment Tensor Potential: Shapeev, A. V. Moment tensor potentials: A class of systematically improvable interatomic potentials. Multiscale Modeling & Simulation, 14(3), 1153-1173. doi:10.1137/15M1054183
Neural Network Potential: Behler, J., & Parrinello, M. Generalized neural-network representation of high-dimensional potential-energy surfaces. Physical Review Letters 2007, 98, 146401. doi:10.1103/PhysRevLett.98.146401
Spectral Neighbor Analysis Potential: Thompson, A. P., Swiler, L. P., Trott, C. R., Foiles, S. M., & Tucker, G. J. Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials. Journal of Computational Physics, 285, 316-330. doi:10.1016/j.jcp.12.018