Abstract
We introduce ACEpotentials.jl, a Julia-language software package that constructs interatomic potentials from quantum mechanical reference data using the Atomic Cluster Expansion [R. Drautz, Phys. Rev. B 99, 014104 (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.
| Original language | English |
|---|---|
| Article number | 164101 |
| Number of pages | 19 |
| Journal | The Journal of Chemical Physics |
| Volume | 159 |
| Issue number | 16 |
| DOIs | |
| Publication status | Published - 21 Oct 2023 |
Bibliographical note
Acknowledgments:G.C. acknowledges support from EPSRC Grant No. EP/X035956/1. C.O., A.R., and T.J. were supported by NSERC Discovery Grant No. GR019381 and NFRF Exploration Grant No. GR022937. W.J.B. was supported by US AFRL Grant No. FA8655-21-1-7010. C.v.d.O. and G.C. acknowledge ARCHER2 for which access was obtained via the UKCP consortium and funded by EPSRC Grant No. EP/P022065/1. N.B. was supported by the U.S. Office of Naval Research through the U.S. Naval Research Laboratory’s fundamental research base program. E.G. acknowledges support from the EPSRC Centre for Doctoral Training in Automated Chemical Synthesis Enabled by Digital Molecular Technologies with Grant Reference No. EP/S024220/1. W.C.W. was supported by the Schmidt Science Fellows in partnership with the Rhodes Trust, and additionally acknowledges support from EPSRC (Grant No. EP/V062654/1). J.K. and C.O. acknowledge funding from the Leverhulme Trust under grant RPG-2017-191 and the EPSRC under Grant No. EP/R043612/1. J.K., J.P.D. and G.C. acknowledge support from the NOMAD Centre of Excellence funded by the European Commission under grant agreement 951786. J.K. acknowledges support from the EPSRC under Grant Nos. EP/P002188 and EP/R012474/1. This work was performed using resources provided by the Cambridge Service for Data Driven Discovery (CSD3) operated by the University of Cambridge Research Computing Service (www.csd3.cam.ac.uk), provided by Dell EMC and Intel using Tier-2 funding from the EPSRC (capital Grant No. EP/T022159/1), and DiRAC funding from the STFC (www.dirac.ac.uk). Further computing facilities were provided by the Scientific Computing Research Technology Platform of the University of Warwick.