Accuracy Assessment of Atomistic Neural Network Potentials: The Impact of Cutoff Radius and Message Passing
The Journal of Physical Chemistry A · 23.11.2023 · 127 (46) · 9874-9883
DOI: 10.1021/acs.jpca.3c06024 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Physical Chemistry A, online erschienen am 09.11.2023. Verfasst von Junfan Xia und 2 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Precision and Intelligent Chemistry, Department of Chemical Physics, University of Science and Technology of China, Hefei, Anhui 23…. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 77 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Chinese Academy of Sciences.
Abstract (Originalsprache)
Atomistic neural network potentials have achieved great success in accelerating atomistic simulations in complicated systems in recent years. They are typically based on the atomic decomposition of total properties, truncating the interatomic correlations to a local environment within a given cutoff radius. A more recently developed message passing (MP) neural network framework can, in principle, incorporate nonlocal effects through iteratively correlating some atoms outside the cutoff sphere with atoms inside, a process referred to as MP. However, how the model accuracy depends on the cutoff radius and the MP process has rarely been discussed. In this work, we investigate this dependence using a recursively embedded atom neural network method that possesses both local and MP features, in two representative systems: liquid H2O and solid Al2O3. We focus on how these settings influence predictions for structural and vibrational properties, namely, radial distribution functions (RDFs) and vibrational density of states (VDOSs). We find that while MP lowers test errors of energy and forces in general, it may not improve the prediction for RDFs and/or VDOSs if direct interatomic correlations in the local environment are insufficiently described. A cutoff radius exceeding the first neighbor shell is necessary, beyond which involving MP quickly enhances the model accuracy until convergence. This is a potentially more efficient way to increase the model accuracy than directly increasing the cutoff radius, especially with more memory savings in the GPU implementation. Our findings also suggest that using the mean test error as the measure of the model accuracy alone is inadequate.
Autor:innen und Institutionen
- Key Laboratory of Precision and Intelligent Chemistry, Department of Chemical Physics, University of Science and Technology of China, Hefei, Anhui 230026, China.
- École Polytechnique FFlytech de Lausanne, 1015 Lausanne, Switzerland.
ORCID-Profile: Bin Jiang
Förderung
- National Natural Science Foundation of China
- Chinese Academy of Sciences
Zitieren
APA
Xia, J., Zhang, Y., & Jiang, B. (2023). Accuracy Assessment of Atomistic Neural Network Potentials: The Impact of Cutoff Radius and Message Passing. The Journal of Physical Chemistry A, 127(46), 9874-9883. https://doi.org/10.1021/acs.jpca.3c06024
Vancouver
Xia J, Zhang Y, Jiang B. Accuracy Assessment of Atomistic Neural Network Potentials: The Impact of Cutoff Radius and Message Passing. The Journal of Physical Chemistry A. 2023;127(46):9874-9883. doi:10.1021/acs.jpca.3c06024
BibTeX
@article{Xia2023,
author = {Xia, Junfan and Zhang, Yaolong and Jiang, Bin},
title = {Accuracy Assessment of Atomistic Neural Network Potentials: The Impact of Cutoff Radius and Message Passing},
journal = {The Journal of Physical Chemistry A},
year = {2023},
volume = {127},
number = {46},
pages = {9874--9883},
doi = {10.1021/acs.jpca.3c06024}
}
EUVIMED