ACEpotentials.jl: A Julia Implementation of the Atomic Cluster Expansion
Abstract
We introduce ACEpotentials.jl, a Julia-language software package that constructs interatomic potentials from quantum mechanical reference data using the Atomic Cluster Expansion (Drautz, 2019). As the latter provides a complete description of atomic environments, including invariance to overall translation and rotation as well as permutation of like atoms, the resulting potentials are systematically improvable and data efficient. Furthermore, the descriptor's expressiveness enables use of a linear model, facilitating rapid evaluation and straightforward application of Bayesian techniques for active learning. We summarize the capabilities of ACEpotentials.jl and demonstrate its strengths (simplicity, interpretability, robustness, performance) on a selection of prototypical atomistic modelling workflows.
Cite
@article{arxiv.2309.03161,
title = {ACEpotentials.jl: A Julia Implementation of the Atomic Cluster Expansion},
author = {William C. Witt and Cas van der Oord and Elena Gelžinytė and Teemu Järvinen and Andres Ross and James P. Darby and Cheuk Hin Ho and William J. Baldwin and Matthias Sachs and James Kermode and Noam Bernstein and Gábor Csányi and Christoph Ortner},
journal= {arXiv preprint arXiv:2309.03161},
year = {2023}
}