We present a molecular dynamics scheme which combines first-principles and machine-learning (ML) techniques in a single information-efficient approach. Forces on atoms are either predicted by Bayesian inference or, if necessary, computed by on-the-fly quantum-mechanical (QM) calculations and added to a growing ML database, whose completeness is, thus, never required. As a result, the scheme is accurate and general, while progressively fewer QM calls are needed when a new chemical process is encountered for the second and subsequent times, as demonstrated by tests on crystalline and molten silicon.

Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces

DE VITA, ALESSANDRO
2015

Abstract

We present a molecular dynamics scheme which combines first-principles and machine-learning (ML) techniques in a single information-efficient approach. Forces on atoms are either predicted by Bayesian inference or, if necessary, computed by on-the-fly quantum-mechanical (QM) calculations and added to a growing ML database, whose completeness is, thus, never required. As a result, the scheme is accurate and general, while progressively fewer QM calls are needed when a new chemical process is encountered for the second and subsequent times, as demonstrated by tests on crystalline and molten silicon.
http://journals.aps.org/prl/issues/114/9
File in questo prodotto:
File Dimensione Formato  
MLOTF_PhysRevLett2015.pdf

accesso aperto

Tipologia: Documento in Versione Editoriale
Licenza: Digital Rights Management non definito
Dimensione 352.57 kB
Formato Adobe PDF
352.57 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11368/2868326
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 376
  • ???jsp.display-item.citation.isi??? 367
social impact