Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen: http://dx.doi.org/10.18419/opus-13479
Autor(en): Gubaev, Konstantin
Zaverkin, Viktor
Srinivasan, Prashanth
Duff, Andrew Ian
Kästner, Johannes
Grabowski, Blazej
Titel: Performance of two complementary machine-learned potentials in modelling chemically complex systems
Erscheinungsdatum: 2023
Dokumentart: Zeitschriftenartikel
Seiten: 15
Erschienen in: npj computational materials 9 (2023), No. 129
URI: http://nbn-resolving.de/urn:nbn:de:bsz:93-opus-ds-134984
http://elib.uni-stuttgart.de/handle/11682/13498
http://dx.doi.org/10.18419/opus-13479
ISSN: 2057-3960
Zusammenfassung: Chemically complex multicomponent alloys possess exceptional properties derived from an inexhaustible compositional space. The complexity however makes interatomic potential development challenging. We explore two complementary machine-learned potentials - the moment tensor potential (MTP) and the Gaussian moment neural network (GM-NN) - in simultaneously describing configurational and vibrational degrees of freedom in the Ta-V-Cr-W alloy family. Both models are equally accurate with excellent performance evaluated against density-functional-theory. They achieve root-mean-square-errors (RMSEs) in energies of less than a few meV/atom across 0 K ordered and high-temperature disordered configurations included in the training. Even for compositions not in training, relative energy RMSEs at high temperatures are within a few meV/atom. High-temperature molecular dynamics forces have similarly small RMSEs of about 0.15 eV/Å for the disordered quaternary included in, and ternaries not part of training. MTPs achieve faster convergence with training size; GM-NNs are faster in execution. Active learning is partially beneficial and should be complemented with conventional human-based training set generation.
Enthalten in den Sammlungen:03 Fakultät Chemie

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat 
s41524-023-01073-w.pdf3,75 MBAdobe PDFÖffnen/Anzeigen


Diese Ressource wurde unter folgender Copyright-Bestimmung veröffentlicht: Lizenz von Creative Commons Creative Commons