KLIFF – KIM-based Learning-Integrated Fitting Framework#
KLIFF is an interatomic potential fitting package that can be used to fit both physics-motivated potentials (e.g. the Stillinger-Weber potential) and machine learning potentials (e.g. neural network potential). The trained potential can be deployed with the KIM-API, which is supported by major simulation codes such as LAMMPS, ASE, DL_POLY, and GULP among others.
The Basics
Advanced Topics
Extra Information
If you find KLIFF useful in your research, please cite:
@Article{wen2022kliff,
title = {{KLIFF}: A framework to develop physics-based and machine learning interatomic potentials},
author = {Mingjian Wen and Yaser Afshar and Ryan S. Elliott and Ellad B. Tadmor},
journal = {Computer Physics Communications},
volume = {272},
pages = {108218},
year = {2022},
doi = {10.1016/j.cpc.2021.108218},
}