Augmentation of Universal Potentials for Broad Applications

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avisTidsskriftartikelForskningpeer review

6 Citationer (Scopus)

Abstract

Universal potentials open the door for DFT level calculations at a fraction of their cost. We find that for application to systems outside the scope of its training data, pretrained CHGNet [Deng et al., Nat. Mach. Intell. 5, 1031 (2023)] has the potential to succeed out of the box, but can also fail significantly in predicting the ground state configuration. We demonstrate that via fine-tuning or a Δ-learning approach it is possible to augment the overall performance of universal potentials for specific cluster and surface systems. We utilize this to investigate and explain experimentally observed defects in the Ag(111)-O surface reconstruction and explain the mechanics behind their formation.

OriginalsprogEngelsk
Artikelnummer056201
TidsskriftPhysical Review Letters
Vol/bind134
Nummer5
ISSN0031-9007
DOI
StatusUdgivet - feb. 2025

Fingeraftryk

Dyk ned i forskningsemnerne om 'Augmentation of Universal Potentials for Broad Applications'. Sammen danner de et unikt fingeraftryk.

Citationsformater