Saved in:
Bibliographic Details
Main Authors: Wu, Mengfan, Tan, Junfu, Zhu, Yu, Ren, Jie
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.03547
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913004659933184
author Wu, Mengfan
Tan, Junfu
Zhu, Yu
Ren, Jie
author_facet Wu, Mengfan
Tan, Junfu
Zhu, Yu
Ren, Jie
contents Machine learning has been widely used for predicting material properties. However, efficient prediction of lattice thermal conductivity ($κ_\mathrm{L}$) remains a long-standing challenge, primarily due to the scarcity of high-quality training data. Here we introduce KappaFormer, a physics-aware Transformer architecture that embeds the harmonic-anharmonic decomposition of $κ_\mathrm{L}$ within the network. KappaFormer comprises a harmonic branch pre-trained on large-scale elastic property data and an anharmonic branch fine-tuned on limited experimental $κ_\mathrm{L}$ data, enabling effective knowledge transfer and enhanced generalization. High-throughput screening with KappaFormer identifies multiple candidates with ultralow $κ_\mathrm{L}$, which are further confirmed by first-principles calculations. Physics interpretability further elucidates the vibrational mechanisms governing thermal transport suppression, linking structural motifs to strong anharmonicity. This study provides a generalizable framework for physics-guided machine learning to accelerate the discovery of new materials.
format Preprint
id arxiv_https___arxiv_org_abs_2604_03547
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle KappaFormer: Physics-aware Transformer for lattice thermal conductivity via cross-domain transfer learning
Wu, Mengfan
Tan, Junfu
Zhu, Yu
Ren, Jie
Materials Science
Machine learning has been widely used for predicting material properties. However, efficient prediction of lattice thermal conductivity ($κ_\mathrm{L}$) remains a long-standing challenge, primarily due to the scarcity of high-quality training data. Here we introduce KappaFormer, a physics-aware Transformer architecture that embeds the harmonic-anharmonic decomposition of $κ_\mathrm{L}$ within the network. KappaFormer comprises a harmonic branch pre-trained on large-scale elastic property data and an anharmonic branch fine-tuned on limited experimental $κ_\mathrm{L}$ data, enabling effective knowledge transfer and enhanced generalization. High-throughput screening with KappaFormer identifies multiple candidates with ultralow $κ_\mathrm{L}$, which are further confirmed by first-principles calculations. Physics interpretability further elucidates the vibrational mechanisms governing thermal transport suppression, linking structural motifs to strong anharmonicity. This study provides a generalizable framework for physics-guided machine learning to accelerate the discovery of new materials.
title KappaFormer: Physics-aware Transformer for lattice thermal conductivity via cross-domain transfer learning
topic Materials Science
url https://arxiv.org/abs/2604.03547