This repository is used to store data and code related to the paper A Machine Learning-Based Framework for Predicting the Power Factor of Thermoelectric Materials.
This is a preliminary repository, with only partial data and code made publicly available. For more information, please contact the first author Mr. Yuxuan Zeng or the corresponding authors Dr. Wei Cao, Prof. Ziyu Wang.
@article{ZENG2025102627,
title = {A machine learning-based framework for predicting the power factor of thermoelectric materials},
journal = {Applied Materials Today},
volume = {43},
pages = {102627},
year = {2025},
issn = {2352-9407},
doi = {https://doi.org/10.1016/j.apmt.2025.102627},
url = {https://www.sciencedirect.com/science/article/pii/S2352940725000460},
author = {Yuxuan Zeng and Wei Cao and Tan Peng and Yue Hou and Ling Miao and Ziyu Wang and Jing Shi},
keywords = {Thermoelectric materials, Machine learning, Selenide, Power factor, First principles},
abstract = {Thermoelectric materials represent an innovative energy solution, capable of converting waste heat into usable electrical power. Recent advances have leveraged machine learning to identify new thermoelectric materials, yet challenges remain in balancing applicability, feature complexity, and interpretability. In this study, we introduce an interpretable framework based on ensemble learning and Magpie chemical element features to predict the power factor (PF) of various materials. Our approach yields approximate analytical expressions for PF using simple elemental features, providing both accuracy and transparency. We validate our predictions with density functional theory, successfully identifying two high-PF selenides as promising candidates for thermoelectric applications.}
}