Thermal conductivity predictions with foundation atomistic models
5 affiliations
- 1Theory of Condensed Matter Group of the Cavendish Laboratory, University of Cambridge, Cambridge, UK
- 2Engineering Laboratory, University of Cambridge, Cambridge, UK
- 3Max Planck Institute for Polymer Research, Mainz, Germany
- 4Department of Applied Physics and Applied Mathematics, Columbia University, New York, USA. [email protected]
- 5Theory of Condensed Matter Group of the Cavendish Laboratory, University of Cambridge, Cambridge, UK. [email protected]
Abstract
Advances in machine learning have led to the development of foundation models for atomistic materials chemistry, enabling quantum-accurate descriptions of interatomic forces across chemically diverse compounds at reduced computational cost. Hitherto, the accuracy and utility of these models have been assessed relying on descriptors based on formation energies or idealized harmonic atomic vibrations. Yet, the rigorous and physically interpretable quantification of their capability to describe both realistic anharmonic atomic dynamics and technologically relevant observables remains a pressing problem. Here, we address this problem, leveraging the Wigner formulation of heat transport and the Grüneisen approach to thermal expansion to connect the atomic-physics awareness of foundation models to their utility in predicting experimentally observable thermomechanical properties, presenting standards and fine-tuning protocols needed to achieve first-principles accuracy. We apply our framework to a database of 103 solids with diverse compositions and structures, demonstrating that it overcomes the major bottlenecks of current methods for designing heat-management materials - high cost, limited transferability, or lack of physics awareness - and has the potential to discover materials for technologies ranging from thermal insulation to neuromorphic computing.
Related
- Challenging Atomistic Foundation Models on Disordered Carbons
- Fast and Accurate Equivariant Foundation Models for Atomistic Simulation
- The Thermal Conductivity of Polymer-Derived Amorphous Si-O-C Compounds and Nano-Composites
- Enhanced thermal conductivity of polyurethane composites via microstructural design of 3D interconnected boron nitride networks
- Effect of pyrolysis temperature on the microstructure and thermal conductivity of polymer-derived monolithic and porous SiC ceramics
BibTeX
@article{pota2026thermal,
title = {{Thermal conductivity predictions with foundation atomistic models}},
author = {Balázs Póta and Paramvir Ahlawat and Gábor Cśanyi and Michele Simoncelli},
journal = {Nature Communications},
year = {2026},
month = sep,
doi = {10.1038/s41467-026-76391-w},
url = {https://doi.org/10.1038/s41467-026-76391-w},
note = {CC BY},
}
RIS
TY - JOUR
TI - Thermal conductivity predictions with foundation atomistic models
AU - Balázs Póta
AU - Paramvir Ahlawat
AU - Gábor Cśanyi
AU - Michele Simoncelli
PY - 2026
DA - 2026/09/05
JO - Nature Communications
DO - 10.1038/s41467-026-76391-w
UR - https://doi.org/10.1038/s41467-026-76391-w
AB - Advances in machine learning have led to the development of foundation models for atomistic materials chemistry, enabling quantum-accurate descriptions of interatomic forces across chemically diverse compounds at reduced computational cost. Hitherto, the accuracy and utility of these models have been assessed relying on descriptors based on formation energies or idealized harmonic atomic vibrations. Yet, the rigorous and physically interpretable quantification of their capability to describe both realistic anharmonic atomic dynamics and technologically relevant observables remains a pressing problem. Here, we address this problem, leveraging the Wigner formulation of heat transport and the Grüneisen approach to thermal expansion to connect the atomic-physics awareness of foundation models to their utility in predicting experimentally observable thermomechanical properties, presenting standards and fine-tuning protocols needed to achieve first-principles accuracy. We apply our framework to a database of 103 solids with diverse compositions and structures, demonstrating that it overcomes the major bottlenecks of current methods for designing heat-management materials - high cost, limited transferability, or lack of physics awareness - and has the potential to discover materials for technologies ranging from thermal insulation to neuromorphic computing.
SN - 2041-1723
ER -