Data analytics accelerates the experimental discovery of new thermoelectric materials with extremely high figure of merit

TL;DR

This paper introduces a machine learning approach that accelerates the discovery of high-performance thermoelectric materials, leading to the experimental synthesis of a record-breaking material with a figure of merit of ~2.8.

Contribution

The study presents a novel active-learning framework using symbolic regression and physically informed descriptors to efficiently explore the vast chemical space for thermoelectric materials.

Findings

Identified a compositional trend for superior TE performance.

Synthesized a new thermoelectric material with a figure of merit ~2.8.

Demonstrated the effectiveness of physically informed descriptors in small data sets.

Abstract

Thermoelectric (TE) materials are among very few sustainable yet feasible energy solutions of present time. This huge promise of energy harvesting is contingent on identifying/designing materials having higher efficiency than presently available ones. However, due to the vastness of the chemical space of materials, only its small fraction was scanned experimentally and/or computationally so far. Employing a compressed-sensing based symbolic regression in an active-learning framework, we have not only identified a trend in materials' compositions for superior TE performance, but have also predicted and experimentally synthesized several extremely high performing novel TE materials. Among these, we found Ag$_{0.55}$Cu$_{0.45}$GaTe$_2$ to possess an experimental figure of merit as high as ~2.8 at 827 K, which is a breakthrough in the field. The presented methodology demonstrates the importance and tremendous potential of physically informed descriptors in material science, in particular for relatively small data sets typically available from experiments at well-controlled conditions.