Search

Machine learning is becoming a valuable tool for scientific discovery. Particularly attractive is the application of machine learning methods to the field of materials development, which enables innovations by discovering new and better functional materials. To apply machine learning to actual materials development, close collaboration between scientists and machine learning tools is necessary. However, such collaboration has been so far impeded by the black box nature of many machine learning algorithms. It is often difficult for scientists to interpret the data-driven models from the viewpoint of material science and physics. Here, we demonstrate the development of spin-driven thermoelectric materials with anomalous Nernst effect by using an interpretable machine learning method called factorized asymptotic Bayesian inference hierarchical mixture of experts (FAB/HMEs). Based on prior knowledge of material science and physics, we were able to extract from the interpretable machine learning some surprising correlations and new knowledge about spin-driven thermoelectric materials. Guided by this, we carried out an actual material synthesis that led to the identification of a novel spin-driven thermoelectric material. This material shows the largest thermopower to date.

Heat-flow sensing is expected to be an important technological component of smart thermal management in the future. Conventionally, the thermoelectric (TE) conversion technique, which is based on the Seebeck effect, has been used to measure a heat flow by converting the flow into electric voltage. However, for ubiquitous heat-flow visualization, thin and flexible sensors with extremely low thermal resistance are highly desired. Recently, another type of TE effect, the longitudinal spin Seebeck effect (LSSE), has aroused great interest because the LSSE potentially offers favourable features for TE applications such as simple thin-film device structures. Here we demonstrate an LSSE-based flexible TE sheet that is especially suitable for a heat-flow sensing application. This TE sheet contained a Ni0.2Zn0.3Fe2.5O4 film which was formed on a flexible plastic sheet using a spray-coating method known as “ferrite plating”. The experimental results suggest that the ferrite-plated film, which has a columnar crystal structure aligned perpendicular to the film plane, functions as a unique one-dimensional spin-current conductor suitable for bendable LSSE-based sensors. This newly developed thin TE sheet may be attached to differently shaped heat sources without obstructing an innate heat flux, paving the way to versatile heat-flow measurements and management.