Accurate and Efficient Interatomic Potentials for Dislocations in InP
Thomas Rocke, Thomas Hudson, Richard Beanland, James Kermode

TL;DR
This paper introduces new ACE and MACE interatomic potentials for InP that closely replicate DFT results, outperform previous models in accuracy, and are significantly faster to evaluate.
Contribution
The authors develop and validate new ACE and MACE models for InP that are more accurate and efficient than existing potentials, enabling better simulation of dislocation mobility.
Findings
ACE and MACE models have at most 4% error on dislocation energies.
Models are approximately five times faster than previous potentials.
New models outperform literature potentials in accuracy.
Abstract
We present Atomic Cluster Expansion (ACE) and MACE models trained on a new dataset of Density Functional Theory (DFT) calculations, constructed for the task of studying the mobility of dislocations in Indium Phosphide (InP). The models are validated in a suite of tests against RSCAN DFT, and compared with previously published potentials from literature. Our new models act as much better surrogates for DFT than the literature models: errors on partial dislocation formation energies are at most 4% for both ACE and MACE, compared with 18% for the MACE-MPA foundation model and 42-50% for earlier bespoke potentials. The bespoke MACE model achieves this accuracy while being around five times faster to evaluate than the MP0 and MPA foundation models.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
