bei Google ScholarTitelangaben
Stocker, Sina ; Gasteiger, Johannes ; Becker, Florian ; Günnemann, Stephan ; Margraf, Johannes T.:
How Robust are Modern Graph Neural Network Potentials in Long and Hot Molecular Dynamics Simulations?
In: Machine Learning: Science and Technology.
Bd. 3
(2022)
Heft 4
.
- 045010.
ISSN 2632-2153
DOI: https://doi.org/10.1088/2632-2153/ac9955
Abstract
Graph neural networks (GNNs) have emerged as a powerful machine learning approach for the prediction of molecular properties. In particular, recently proposed advanced GNN models promise quantum chemical accuracy at a fraction of the computational cost. While the capabilities of such advanced GNNs have been extensively demonstrated on benchmark datasets, there have been few applications in real atomistic simulations. Here, we therefore put the robustness of GNN interatomic potentials to the test, using the recently proposed GemNet architecture as a testbed. Models are trained on the QM7-x database of organic molecules and used to perform extensive molecular dynamics simulations. We find that low test set errors are not sufficient for obtaining stable dynamics and that severe pathologies sometimes only become apparent after hundreds of ps of dynamics. Nonetheless, highly stable and transferable GemNet potentials can be obtained with sufficiently large training sets.
Weitere Angaben
| Publikationsform: | Artikel in einer Zeitschrift |
|---|---|
| Begutachteter Beitrag: | Ja |
| Institutionen der Universität: | Fakultäten > Fakultät für Biologie, Chemie und Geowissenschaften > Fachgruppe Chemie > Lehrstuhl Künstliche Intelligenz in der physiko-chemischen Materialanalytik Fakultäten > Fakultät für Biologie, Chemie und Geowissenschaften > Fachgruppe Chemie > Lehrstuhl Künstliche Intelligenz in der physiko-chemischen Materialanalytik > Lehrstuhl Künstliche Intelligenz in der physiko-chemischen Materialanalytik - Univ.-Prof. Dr. Johannes Theo Margraf |
| Titel an der UBT entstanden: | Nein |
| Themengebiete aus DDC: | 500 Naturwissenschaften und Mathematik > 540 Chemie |
| Eingestellt am: | 13 Nov 2023 13:45 |
| Letzte Änderung: | 13 Nov 2023 13:45 |
| URI: | https://eref.uni-bayreuth.de/id/eprint/87657 |