Iwasaki Yuma, Takeuchi Ichiro, Stanev Valentin, Kusne Aaron Gilad, Ishida Masahiko, Kirihara Akihiro, Ihara Kazuki, Sawada Ryohto, Terashima Koichi, Someya Hiroko, Uchida Ken-Ichi, Saitoh Eiji, Yorozu Shinichi
Central Research Laboratories, NEC Corporation, Tsukuba, 305-8501, Japan.
PRESTO, JST, Saitama, 322-0012, Japan.
Sci Rep. 2019 Feb 26;9(1):2751. doi: 10.1038/s41598-019-39278-z.
Thermoelectric technologies are becoming indispensable in the quest for a sustainable future. Recently, an emerging phenomenon, the spin-driven thermoelectric effect (STE), has garnered much attention as a promising path towards low cost and versatile thermoelectric technology with easily scalable manufacturing. However, progress in development of STE devices is hindered by the lack of understanding of the fundamental physics and materials properties responsible for the effect. In such nascent scientific field, data-driven approaches relying on statistics and machine learning, instead of more traditional modeling methods, can exhibit their full potential. Here, we use machine learning modeling to establish the key physical parameters controlling STE. Guided by the models, we have carried out actual material synthesis which led to the identification of a novel STE material with a thermopower an order of magnitude larger than that of the current generation of STE devices.
热电技术在追求可持续未来的过程中变得不可或缺。最近，一种新兴现象——自旋驱动热电效应（STE），作为通往低成本、通用且易于扩展制造的热电技术的一条有前途的途径，备受关注。然而，由于对导致该效应的基本物理和材料特性缺乏了解，STE 器件的开发进展受到阻碍。在这样一个新兴的科学领域，依赖统计和机器学习的数据驱动方法，而非更传统的建模方法，能够充分发挥其潜力。在此，我们使用机器学习建模来确定控制 STE 的关键物理参数。在这些模型的指导下，我们进行了实际的材料合成，从而鉴定出一种新型的 STE 材料，其热功率比当前一代 STE 器件大一个数量级。
