E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials

Simon Batzner (), Albert Musaelian, Lixin Sun, Mario Geiger, Jonathan P. Mailoa, Mordechai Kornbluth, Nicola Molinari, Tess E. Smidt and Boris Kozinsky ()
Additional contact information
Simon Batzner: Harvard University
Albert Musaelian: Harvard University
Lixin Sun: Harvard University
Mario Geiger: École Polytechnique Fédérale de Lausanne
Jonathan P. Mailoa: Robert Bosch Research and Technology Center
Mordechai Kornbluth: Robert Bosch Research and Technology Center
Nicola Molinari: Harvard University
Tess E. Smidt: Lawrence Berkeley National Laboratory
Boris Kozinsky: Harvard University

Nature Communications, 2022, vol. 13, issue 1, 1-11

Abstract: Abstract This work presents Neural Equivariant Interatomic Potentials (NequIP), an E(3)-equivariant neural network approach for learning interatomic potentials from ab-initio calculations for molecular dynamics simulations. While most contemporary symmetry-aware models use invariant convolutions and only act on scalars, NequIP employs E(3)-equivariant convolutions for interactions of geometric tensors, resulting in a more information-rich and faithful representation of atomic environments. The method achieves state-of-the-art accuracy on a challenging and diverse set of molecules and materials while exhibiting remarkable data efficiency. NequIP outperforms existing models with up to three orders of magnitude fewer training data, challenging the widely held belief that deep neural networks require massive training sets. The high data efficiency of the method allows for the construction of accurate potentials using high-order quantum chemical level of theory as reference and enables high-fidelity molecular dynamics simulations over long time scales.

Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (24)

Downloads: (external link)
https://www.nature.com/articles/s41467-022-29939-5 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-29939-5

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-022-29939-5

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().