Stability and transferability of machine learning force fields for molecular dynamics applications
Digital Discovery · 2024 · 3 (11) · 2177-2182
DOI: 10.1039/d4dd00140k ↗Kurz gefasst
Fachartikel in der Zeitschrift Digital Discovery, 2024. Verfasst von Salatan Duangdangchote und 2 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 3.0). Gefördert von: Canada First Research Excellence Fund, University of Toronto, Natural Sciences and Engineering Research Council of Canada.
Abstract (Originalsprache)
We benchmark GNN models for MLFF-MD and introduce new metrics beyond conventional force and energy errors. Our approach, demonstrated on lithium-ion conductors, aims to broaden ionic conductor screening for batteries.
Förderung
- Canada First Research Excellence Fund
- University of Toronto
- Natural Sciences and Engineering Research Council of Canada
Zitieren
APA
Duangdangchote, S., Seferos, D. S., & Voznyy, O. (2024). Stability and transferability of machine learning force fields for molecular dynamics applications. Digital Discovery, 3(11), 2177-2182. https://doi.org/10.1039/d4dd00140k
Vancouver
Duangdangchote S, Seferos DS, Voznyy O. Stability and transferability of machine learning force fields for molecular dynamics applications. Digital Discovery. 2024;3(11):2177-2182. doi:10.1039/d4dd00140k
BibTeX
@article{Duangdangchote2024,
author = {Duangdangchote, Salatan and Seferos, Dwight S. and Voznyy, Oleksandr},
title = {Stability and transferability of machine learning force fields for molecular dynamics applications},
journal = {Digital Discovery},
year = {2024},
volume = {3},
number = {11},
pages = {2177--2182},
doi = {10.1039/d4dd00140k}
}
EUVIMED