Atomic cluster expansion for accurate and transferable interatomic potentials

By Ralf Drautz. Physical review B, 2019

749 citations recorded by the source corpus.

Subfields: Materials Chemistry, Physical and Theoretical Chemistry

View Paper: https://www.semanticscholar.org/paper/462d01edc820ac0d4f4460ed133b0f59a292ff9e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Materials Chemistry

In Physical and Theoretical Chemistry

Citations in the corpus

Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport (2021, neutral): “The connections between different atom environment descriptors have been revealed recently [33, 41].”
Machine-Learning Interatomic Potentials for Materials Science (2021, background): “N0 0 014-18-1-2612 . eclaration of Competing Interest The authors declare that they have no known competing finanial interests or personal relationships that could have appeared to nfluence the work reported in this paper. ppendix A. Table of abbreviations ACE Atomic cluster expansion AIMD Ab initio”
E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials (2021, methodology): “The results for ACE, GAP, and ANI on the revised MD-17 data set are those reported in [43].”
MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields (2022, background): “First, the Atomic Cluster Expansion (ACE) [16] provided a systematic framework for constructing high body order complete polynomial basis functions (features) at a constant cost per basis function, independent of body order [17].”
The design space of E(3)-equivariant atom-centred interatomic potentials (2022, positive): “The models then apply a series of convolution or message passing operations on this graph to learn a representation of the environment of each atom.”
The MLIP package: moment tensor potentials with MPI and active learning (2020, methodology): “MTPs, like SOAP-GAP, are not based on solely two- and three-body descriptors and can provably approximate an arbitrary local interaction, and so are ACE [18] and PIP [75].”
Learning local equivariant representations for large-scale atomistic dynamics (2022, methodology): “• O(1) in the number of species S, unlike local descriptors such as SOAP (O(S(2))) or ACE (O(S order−1)) [12].”