A recommendation engine for suggesting unexpected thermoelectric chemistries

TL;DR

This paper introduces a machine learning recommendation engine that suggests novel thermoelectric materials, successfully identifying promising chemistries different from traditional families and experimentally validating one such example with notable performance.

Contribution

The study presents an open ML-based tool to guide thermoelectric material discovery, bridging the gap between computational predictions and experimental synthesis efforts.

Findings

Engine can identify promising new thermoelectric chemistries.

Experimental validation of RE12Co5Bi compounds shows unexpected thermoelectric performance.

Engine suggests chemistries with high metallic element loading for thermoelectric applications.

Abstract

The experimental search for new thermoelectric materials remains largely confined to a limited set of successful chemical and structural families, such as chalcogenides, skutterudites, and Zintl phases. In principle, computational tools such as density functional theory (DFT) offer the possibility of rationally guiding experimental synthesis efforts toward very different chemistries. However, in practice, predicting thermoelectric properties from first principles remains a challenging endeavor, and experimental researchers generally do not directly use computation to drive their own synthesis efforts. To bridge this practical gap between experimental needs and computational tools, we report an open machine learning-based recommendation engine (http://thermoelectrics.citrination.com) for materials researchers that suggests promising new thermoelectric compositions, and evaluates the feasibility of user-designed compounds. We show that this engine can identify interesting chemistries very different from known thermoelectrics. Specifically, we describe the experimental characterization of one example set of compounds derived from our engine, RE12Co5Bi (RE = Gd, Er), which exhibits surprising thermoelectric performance given its unprecedentedly high loading with metallic d and f block elements, and warrants further investigation as a new thermoelectric material platform.