Defect-limited thermal transport in AlN using pretrained machine-learning interatomic potentials

Abstract

Aluminum nitride (AlN) is an important thermal management material whose high lattice thermal conductivity is strongly suppressed by oxygen impurities. We investigate phonon scattering by oxygen-related defects using pretrained universal machine-learning interatomic potentials (MLIPs), molecular dynamics (MD), and phonon Boltzmann transport calculations. Several pretrained MLIPs are benchmarked against density functional theory for phonon dispersions and pristine thermal conductivity. To balance accuracy and computational speed, we use a fine-tuned version of the compact SevenNet-Nano model for MD simulations. Monte Carlo annealing supports the formation of bound V_Al(O_N)₃ complexes, whose scattering differs from that of their isolated constituents. Defect scattering rates extracted from excess spectral energy density (SED) linewidths agree reasonably with harmonic T-matrix predictions at low oxygen contents, supporting the independent-scatterer approximation. Incorporating these rates into an iterative Boltzmann transport equation with Bose--Einstein statistics yields thermal conductivities comparable to experimental values and captures their observed decrease with oxygen content. At high concentrations, however, the scattering rate deviates from linear scaling with oxygen content, suggesting limitations of independent-defect and pristine-phonon descriptions. These results demonstrate an efficient approach using pretrained MLIPs to quantify defect-limited thermal transport and provide insights into impurity effects beyond the dilute-defect approximation.

Distilling Large-Scale Machine Learning Interatomic Potentials to Predict Long-Timescale Electrolyte Transport Properties
Ishan Amin, Yue Jian, Nitesh Kumar +10
arXiv29 Oct 2026PreprintCC BY 4.0Full textPhysical chemistry Computational physicsarXiv
NEP-kappa 2.0: A unified framework for phonon transport and nonequilibrium thermalization with machine-learning interatomic potentials
Shixian Liu, Bin Liu, Fei Yin +8
arXiv18 Oct 2026PreprintarXiv licenceFull textComputational physics Condensed matterarXiv
Benchmarking machine-learning interatomic potentials using classical force fields
Johannes Sandberg, Geneviève Dusson, Julien Lam
arXiv9 Oct 2026PreprintCC BY 4.0Full textCondensed matterarXiv
Thermal expansion mechanisms, heat transport, and band-gap renormalization in strongly anharmonic Rb₂SO₄, Rb₂Ca₂(SO₄)₃, and Ba₃Lu(BO₃)₃ from machine-learned interatomic potentials
Ekaterina Spirande, Rustam Arabov, Sofya Demina +2
arXiv22 Oct 2026PreprintCC BY-NC-ND 4.0Full textCondensed matterarXiv
MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials
Ryuhei Okuno, Nontawat Charoenphakdee, Kaoru Hisama +1
arXiv8 Sep 2026PreprintCC BY 4.0Full textPhysical chemistry Condensed matterarXiv

Cite

BibTeX RIS

BibTeX

@misc{moon2026defectlimited,
  title = {{Defect-limited thermal transport in AlN using pretrained machine-learning interatomic potentials}},
  author = {Minseok Moon and Wonjun Choi and Seungwu Han and Youngho Kang},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.08013},
  eprint = {2610.08013},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.08013},
}

RIS

TY  - UNPB
TI  - Defect-limited thermal transport in AlN using pretrained machine-learning interatomic potentials
AU  - Minseok Moon
AU  - Wonjun Choi
AU  - Seungwu Han
AU  - Youngho Kang
PY  - 2026
DA  - 2026/10/06
PB  - arXiv
DO  - 10.48550/arxiv.2610.08013
UR  - https://arxiv.org/abs/2610.08013
AB  - Aluminum nitride (AlN) is an important thermal management material whose high lattice thermal conductivity is strongly suppressed by oxygen impurities. We investigate phonon scattering by oxygen-related defects using pretrained universal machine-learning interatomic potentials (MLIPs), molecular dynamics (MD), and phonon Boltzmann transport calculations. Several pretrained MLIPs are benchmarked against density functional theory for phonon dispersions and pristine thermal conductivity. To balance accuracy and computational speed, we use a fine-tuned version of the compact SevenNet-Nano model for MD simulations. Monte Carlo annealing supports the formation of bound V_Al(O_N)_3 complexes, whose scattering differs from that of their isolated constituents. Defect scattering rates extracted from excess spectral energy density (SED) linewidths agree reasonably with harmonic T-matrix predictions at low oxygen contents, supporting the independent-scatterer approximation. Incorporating these rates into an iterative Boltzmann transport equation with Bose--Einstein statistics yields thermal conductivities comparable to experimental values and captures their observed decrease with oxygen content. At high concentrations, however, the scattering rate deviates from linear scaling with oxygen content, suggesting limitations of independent-defect and pristine-phonon descriptions. These results demonstrate an efficient approach using pretrained MLIPs to quantify defect-limited thermal transport and provide insights into impurity effects beyond the dilute-defect approximation.
ER  -

Abstract

Related

Cite