2026-06-01T07:15:22Zhttps://www.radar-service.eu/oai/OAIHandler10.35097/k9kebu3yb0cc8xcm2026-05-19T10:40:36Zradar4kit
10.35097/k9kebu3yb0cc8xcm
Sireci, Enrico
Enrico
Sireci
Institut für Katalyseforschung und -technologie (IKFT), Karlsruher Institut für Technologie (KIT)
Sharapa, D. I.
D. I.
Sharapa
0000-0001-9510-9081
Institut für Katalyseforschung und -technologie (IKFT), Karlsruher Institut für Technologie (KIT)
Studt, F.
F.
Studt
Institut für Katalyseforschung und -technologie (IKFT), Karlsruher Institut für Technologie (KIT)
Fine-Tuned Machine-Learning Potential for Accurate Description of Mn$_x$O$_y$H$_z$ Clusters on Cobalt Surfaces
Karlsruhe Institute of Technology
2026
2026
Chemistry
DFT
uMLP
Fine-Tuning
Open Access
Creative Commons Attribution Share Alike 4.0 International
Sireci, Enrico
Sharapa, D. I.
0000-0001-9510-9081
Studt, F.
In this document, we present a fine-tuned version of the universal machine-learning po- tential (uMLP) CHGNet to accurately model MnxOyHz clusters on fcc-Co Surfaces. The pdf file explaining the procedure is divided in three sections: the first specifies the density functional theory (DFT) settings employed for the single-point (SP) calculations used for structures labeling, the second is related to the creation of the structure database and the third to the training procedure. The structural database file used for the fine-tuning procedure is provided as both an ase .db and .json file.
The structural database of MnxOyHz clusters adsorbed on Co surfaces is provided as ase .db and .json files. The pdf file provides explanation regarding the database creation and machine-learning potential fine-tuning procedure.
https://publikationen.bibliothek.kit.edu/1000193127
61,2 MB
application/x-tar