Materials development by interpretable machine learning

TL;DR

This paper demonstrates how interpretable machine learning, specifically FAB/HMEs, can facilitate scientific discovery in materials development by uncovering novel correlations and guiding the synthesis of new thermoelectric materials.

Contribution

It introduces the use of interpretable FAB/HMEs in materials science, enabling scientists to interpret models and discover new materials.

Findings

Discovered a surprising correlation in thermoelectric materials.

Guided the synthesis of a novel spin-driven thermoelectric material.

Achieved the largest thermopower to date in the new material.

Abstract

Machine learning technologies are expected to be great tools for scientific discoveries. In particular, materials development (which has brought a lot of innovation by finding new and better functional materials) is one of the most attractive scientific fields. To apply machine learning to actual materials development, collaboration between scientists and machine learning is becoming inevitable. However, such collaboration has been restricted so far due to black box machine learning, in which it is difficult for scientists to interpret the data-driven model from the viewpoint of material science and physics. Here, we show a material development success story that was achieved by good collaboration between scientists and one type of interpretable (explainable) machine learning called factorized asymptotic Bayesian inference hierarchical mixture of experts (FAB/HMEs). Based on material science and physics, we interpreted the data-driven model constructed by the FAB/HMEs, so that we discovered surprising correlation and knowledge about thermoelectric material. Guided by this, we carried out actual material synthesis that led to identification of a novel spin-driven thermoelectric material with the largest thermopower to date.