Unsupervised machine learning for discovery of promising half-Heusler thermoelectric materials

• Published in: npj computational materials Vol. 8; no. 1; pp. 1 - 9
• Main Authors: Jia, Xue, Deng, Yanshuai, Bao, Xin, Yao, Honghao, Li, Shan, Li, Zhou, Chen, Chen, Wang, Xinyu, Mao, Jun, Cao, Feng, Sui, Jiehe, Wu, Junwei, Wang, Cuiping, Zhang, Qian, Liu, Xingjun
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 04.03.2022; Nature Portfolio
• Subjects: 639/166/987; 639/301/299/2736; Characterization and Evaluation of Materials; Chemistry and Materials Science; Computational Intelligence; Materials Science; Mathematical and Computational Engineering; Mathematical and Computational Physics; Mathematical Modeling and Industrial Mathematics; Theoretical
• ISSN: 2057-3960; 2057-3960
• DOI: 10.1038/s41524-022-00723-9

Thermoelectric materials can be potentially applied to waste heat recovery and solid-state cooling because they allow a direct energy conversion between heat and electricity and vice versa. The accelerated materials design based on machine learning has enabled the systematic discovery of promising materials. Herein we proposed a successful strategy to discover and design a series of promising half-Heusler thermoelectric materials through the iterative combination of unsupervised machine learning with the labeled known half-Heusler thermoelectric materials. Subsequently, optimized zT values of ~0.5 at 925 K for p-type Sc 0.7 Y 0.3 NiSb 0.97 Sn 0.03 and ~0.3 at 778 K for n-type Sc 0.65 Y 0.3 Ti 0.05 NiSb were experimentally achieved on the same parent ScNiSb.