A review of machine learning approaches for the discovery of thermoelectric materials

Abstract

Thermoelectric (TE) materials have garnered significant interest due to their capacity to convert heat directly into electrical energy and vice versa, offering a sustainable route for energy harvesting and waste heat recovery. Nevertheless, many of the high-performance TE materials reported to date rely on elements that are scarce, costly, or environmentally hazardous, thereby limiting their large-scale deployment. To overcome these challenges, the development of efficient, earth-abundant, and environmentally benign alternatives is essential. Although first-principles methods provide valuable insights into the transport behavior of potential TE materials, their high computational cost restricts their utility in large-scale material screening. Recent progress in computational infrastructure, along with the advent of data-centric approaches such as machine learning (ML), has transformed the landscape of thermoelectric research. ML algorithms, trained on comprehensive datasets including experimental measurements, crystallographic data, and density functional theory (DFT) results can predict key TE metrics, such as the figure of merit (ZT), with remarkable speed and accuracy. This review explores the integration of ML into TE materials discovery, emphasizing its role in property prediction, descriptor engineering, and structural optimization. A systematic examination of ML-driven strategies promises to accelerate the discovery process and improve the efficiency of next-generation thermoelectric systems.