Driving Thermoelectric Optimization in AgSbTe2 via Design of Experiments and Machine Learning

Systemic optimization of thermoelectric materials is arduous due to their conflicting electrical and thermal properties. A strategy based on Design of Experiments and machine learning is developed to optimize the thermoelectric efficiency of AgSb_1+xTe_2+y, an established thermoelectric. From eight experiments, high thermoelectric performance in AgSb_1.021Te_2.04 is revealed with a peak and average thermoelectric figure of merit of 1.61 ± 0.24 at 600 K and 1.18 ± 0.18 (300–623 K), respectively, which is >30% higher than the best literature values for AgSb_1+xTe_2+y. Ag deficiency and suppression of secondary phases in AgSb_1.021Te_2.04 improve the electrical properties and reduce the thermal conductivity (∼0.4 W m^–1 K^–1). Our strategy is implemented into an open-source graphical user interface, and it can be used to optimize the methodologies, properties, and processes across different scientific fields.