How to validate machine-learned interatomic potentials
The Journal of Chemical Physics · 28.03.2023 · 158 (12)
DOI: 10.1063/5.0139611 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Chemical Physics, online erschienen am 24.03.2023. Verfasst von Joe D Morrow und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemistry, Inorganic Chemistry Laboratory, University of Oxford, Oxford OX1 3QR, United Kingdom. Die Arbeit wurde bisher 139-mal zitiert (Crossref) und nennt 97 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Engineering and Physical Sciences Research Council, UK Research and Innovation.
Abstract (Originalsprache)
Machine learning (ML) approaches enable large-scale atomistic simulations with near-quantum-mechanical accuracy. With the growing availability of these methods, there arises a need for careful validation, particularly for physically agnostic models—that is, for potentials that extract the nature of atomic interactions from reference data. Here, we review the basic principles behind ML potentials and their validation for atomic-scale material modeling. We discuss the best practice in defining error metrics based on numerical performance, as well as physically guided validation. We give specific recommendations that we hope will be useful for the wider community, including those researchers who intend to use ML potentials for materials “off the shelf.”
Autor:innen und Institutionen
- Department of Chemistry, Inorganic Chemistry Laboratory, University of Oxford, Oxford OX1 3QR, United Kingdom.
ORCID-Profile: Joe D Morrow, John L A Gardner, Volker L Deringer
Förderung
- Engineering and Physical Sciences Research Council
- UK Research and Innovation
Zitieren
APA
Morrow, J. D., Gardner, J. L. A., & Deringer, V. L. (2023). How to validate machine-learned interatomic potentials. The Journal of Chemical Physics, 158(12). https://doi.org/10.1063/5.0139611
Vancouver
Morrow JD, Gardner JLA, Deringer VL. How to validate machine-learned interatomic potentials. The Journal of Chemical Physics. 2023;158(12). doi:10.1063/5.0139611
BibTeX
@article{Morrow2023,
author = {Morrow, Joe D and Gardner, John L A and Deringer, Volker L},
title = {How to validate machine-learned interatomic potentials},
journal = {The Journal of Chemical Physics},
year = {2023},
volume = {158},
number = {12},
doi = {10.1063/5.0139611}
}
EUVIMED