Charge-constrained atomic cluster expansion

The atomic cluster expansion (ACE) efficiently parametrizes complex energy surfaces of pure elements and alloys. Due to the local nature of the many-body basis, ACE is inherently local or semilocal for graph ACE. Here, we employ descriptor-constrained density-functional theory (DFT) for parametrizing ACE with charge or other degrees of freedom, thereby transfering the variational property of the density functional to ACE. The descriptors can be of scalar, vectorial, or tensorial nature. From the simplest case of scalar atomic descriptors we directly obtain charge-dependent ACE with long-range electrostatic interactions between variable charges. We observe that the variational properties of the charges greatly help in training, avoiding the need for charge-constrained DFT calculations.

Authors

Institutions

Publication Details

Journal
Physical Review Materials
Published
2025-03-04
DOI
https://doi.org/10.1103/physrevmaterials.9.033802
Citations
14
Primary Topic
Machine Learning in Materials Science
Type
article
Field-Weighted Citation Impact
6.73

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Charge-constrained atomic cluster expansion

Ralf Drautz, Yury V. Lysogorskiy, Matteo Rinaldi, Anton S. Bochkarev
14 citations
Physical Review Materials
Machine Learning in Materials Science
6.73
article

Charge-constrained atomic cluster expansion

Ralf Drautz, Yury V. Lysogorskiy, Matteo Rinaldi, Anton S. Bochkarev
article en
14 citations

Abstract

The atomic cluster expansion (ACE) efficiently parametrizes complex energy surfaces of pure elements and alloys. Due to the local nature of the many-body basis, ACE is inherently local or semilocal for graph ACE. Here, we employ descriptor-constrained density-functional theory (DFT) for parametrizing ACE with charge or other degrees of freedom, thereby transfering the variational property of the density functional to ACE. The descriptors can be of scalar, vectorial, or tensorial nature. From the simplest case of scalar atomic descriptors we directly obtain charge-dependent ACE with long-range electrostatic interactions between variable charges. We observe that the variational properties of the charges greatly help in training, avoiding the need for charge-constrained DFT calculations.

Physical Review MaterialsVol. 9(3)
Ruhr University Bochum (DE)
Deutsche Forschungsgemeinschaft
Openalex Percentile: Top 3%
Machine Learning in Materials Science
6.73
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Charge-constrained atomic cluster expansion — Ralf Drautz, Yury V. Lysogorskiy, et al. · Physical Review Materials (2025) | TGRS Research Map | TGRS