Using Machine-Learned Force Fields for Describing Heat-Transport-Related Quantities in AlGaN and Derived Materials
Condensed Matter · 11.06.2026 · 11 (2) · 23
DOI: 10.3390/condmat11020023 ↗Kurz gefasst
Fachartikel in der Zeitschrift Condensed Matter, online erschienen am 11.06.2026. Verfasst von Simon Fernbach und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 100 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
In this work, we develop machine-learned moment tensor potentials (MTPs) to simulate the static and dynamic structural properties in AlxGa1−xN and related materials. The potentials are trained on DFT-calculated data for forces, stresses, and energies obtained from random atomic displacements and cell deformations. MTP-calculated physical properties, including lattice parameters and elastic constants, thermal expansion, harmonic and anharmonic vibrational properties, and the thermal conductivity, are benchmarked against first-principles results and experimental data. The comparisons testify to the very high accuracy achieved by the machine-learned potentials despite the massively reduced computational effort. Additionally, the impact of various aspects of the MTP training procedure is examined.
Zitieren
APA
Fernbach, S., Zojer, E., & Bedoya-Martínez, N. (2026). Using Machine-Learned Force Fields for Describing Heat-Transport-Related Quantities in AlGaN and Derived Materials. Condensed Matter, 11(2), 23. https://doi.org/10.3390/condmat11020023
Vancouver
Fernbach S, Zojer E, Bedoya-Martínez N. Using Machine-Learned Force Fields for Describing Heat-Transport-Related Quantities in AlGaN and Derived Materials. Condensed Matter. 2026;11(2):23. doi:10.3390/condmat11020023
BibTeX
@article{Fernbach2026,
author = {Fernbach, Simon and Zojer, Egbert and Bedoya-Martínez, Natalia},
title = {Using Machine-Learned Force Fields for Describing Heat-Transport-Related Quantities in AlGaN and Derived Materials},
journal = {Condensed Matter},
year = {2026},
volume = {11},
number = {2},
pages = {23},
doi = {10.3390/condmat11020023}
}
EUVIMED