Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials

Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials

Abstract Efficiently creating a concise but comprehensive data set for training machine-learned interatomic potentials (MLIPs) is an under-explored problem. Active learning, which uses biased or unbiased molecular dynamics (MD) to generate candidate pools, aims to address this objective. Existing bi...

Cur síos iomlán

Sonraí bibleagrafaíochta
Príomhchruthaitheoirí: Viktor Zaverkin, David Holzmüller, Henrik Christiansen, Federico Errica, Francesco Alesiani, Makoto Takamoto, Mathias Niepert, Johannes Kästner
Formáid: Alt
Teanga:English
Foilsithe / Cruthaithe: Nature Portfolio 2024-04-01
Sraith:npj Computational Materials
Rochtain ar líne:https://doi.org/10.1038/s41524-024-01254-1

Ar líne

https://doi.org/10.1038/s41524-024-01254-1

Míreanna comhchosúla