SNUMAT's package

SIMPLE NN

SIMPLE-NN uses ASE to handle output from ab initio programs like VASP or Quantum espresso.

All output types supported by ASE can be used in SIMPLE-NN, but they need to contain essential information such as atom coordinates, lattice parameters, energy, and forces. (Release_notes)

Download

Requirements

  1. LAMMPS
  2. Tensorflow >= r1.6.
  3. PYTHON - 2.7.X or 3.4 - 3.6 (http://www.python.org/)
  4. mpi4py (optional)

Contact

E-mail: amp2.mtcg@gmail.com

Licence

The BSD 3-Clause Licence

How to cite:

If you used SIMPLE-NN for your work, please cite the following article.

  • "Toward Reliable and Transferable Machine Learning Potentials: Uniform Training by Overcoming Sampling Bias"
    Wonseok Jeong, Kyuhyun Lee, Dongsun Yoo, Dongheon Lee, and Seungwu Han, J. Phys. Chem. 7, pp 22790-22795 (2018)
    https://pubs.acs.org/doi/10.1021/acs.jpcc.8b08063