AI‐Driven Defect Engineering for Advanced Thermoelectric Materials

Abstract

Thermoelectric materials offer a promising pathway to directly convertwaste heat to electricity. However, achieving high performance remainschallenging due to intrinsic trade-offs between electrical conductivity, theSeebeck coefficient, and thermal conductivity, which are further complicatedby the presence of defects. This review explores how artificial intelligence (AI)and machine learning (ML) are transforming thermoelectric materials design.Advanced ML approaches including deep neural networks, graph-basedmodels, and transformer architectures, integrated with high-throughputsimulations and growing databases, effectively capture structure-propertyrelationships in a complex multiscale defect space and overcome the “curse ofdimensionality”. This review discusses AI-enhanced defect engineering strate-gies such as composition optimization, entropy and dislocation engineering,and grain boundary design, along with emerging inverse design techniquesfor generating materials with targeted properties. Finally, it outlines futureopportunities in novel physics mechanisms and sustainability, highlightingthe critical role of AI in accelerating the discovery of thermoelectric materials.