The Cartesian Atomic Cluster Expansion (CACE) is a new approach for developing machine learning interatomic potentials. This method utilizes Cartesian coordinates to provide a complete description of atomic environments, maintaining interaction body orders. It integrates low-dimensional embeddings of chemical elements with inter-atomic message passing.
- Python 3.6 or higher
- NumPy
- ASE (Atomic Simulation Environment)
- PyTorch
- matscipy
Please refer to the setup.py file for installation instructions.
Please refer to the scripts/train.py.
More example scripts can be found in [https://github.com/BingqingCheng/cacefit].
This project is licensed under the MIT License - see the LICENSE file for details.
@article{cheng2024cartesian,
title={Cartesian atomic cluster expansion for machine learning interatomic potentials},
author={Cheng, Bingqing},
journal={npj Computational Materials},
volume={10},
number={1},
pages={157},
year={2024},
publisher={Nature Publishing Group UK London}
}
For any queries regarding CACE, please contact Bingqing Cheng at [email protected].