Learning thermoelectric transport from crystal structures via multiscale graph neural network
Physical Review Applied · 07.07.2026 · 26 (1)
DOI: 10.1103/m8nb-bbp8 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physical Review Applied, online erschienen am 07.07.2026. Verfasst von Yuxuan Zeng und 9 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 126 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Zhongnan Hospital of Wuhan University.
Abstract (Originalsprache)
Graph neural networks (GNNs) are designed to extract latent patterns from graph-structured data, making them particularly well suited for crystal representation learning. Here, we propose a GNN model tailored for estimating electronic transport coefficients in inorganic thermoelectric crystals. The model encodes crystal structures and physicochemical properties in a multiscale manner, encompassing global, atomic, bond, and angular levels. It achieves state-of-the-art performance on benchmark datasets with remarkable extrapolative capability. By combining the proposed GNN with \textit{ab initio} calculations, we successfully identify compounds exhibiting outstanding electronic transport properties and further perform interpretability analyses from both global and atomic perspectives, tracing the origins of their distinct transport behaviors. Interestingly, the decision process of the model naturally reveals underlying physical patterns, offering new insights into computer-assisted materials design.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Zhongnan Hospital of Wuhan University
- Fundamental Research Funds for the Central Universities
- Wuhan University
- Translational Medicine and Interdisciplinary Research
Zitieren
APA
Zeng, Y., Cao, W., Zuo, Y., Lyu, F., Xie, W., Peng, T., Hou, Y., Miao, L., Wang, Z., & Shi, J. (2026). Learning thermoelectric transport from crystal structures via multiscale graph neural network. Physical Review Applied, 26(1). https://doi.org/10.1103/m8nb-bbp8
Vancouver
Zeng Y, Cao W, Zuo Y, Lyu F, Xie W, Peng T, et al. Learning thermoelectric transport from crystal structures via multiscale graph neural network. Physical Review Applied. 2026;26(1). doi:10.1103/m8nb-bbp8
BibTeX
@article{Zeng2026,
author = {Zeng, Yuxuan and Cao, Wei and Zuo, Yijing and Lyu, Fang and Xie, Wenhao and Peng, Tan and Hou, Yue and Miao, Ling and Wang, Ziyu and Shi, Jing},
title = {Learning thermoelectric transport from crystal structures via multiscale graph neural network},
journal = {Physical Review Applied},
year = {2026},
volume = {26},
number = {1},
doi = {10.1103/m8nb-bbp8}
}
EUVIMED