Bayesian optimization improved the thermoelectric properties of InGaAsSb thin films; this domain warrants comprehensive investigation due to the need to simultaneously control multiple parameters, such as, the composition, dopant concentration, and film-deposition temperatures. After six optimization cycles, the dimensionless figure of merit exhibited an approximately threefold improvement compared to its values obtained in the random initial experimental trials. These findings not only promote the development of thermoelectric devices based on III–V semiconductors but also highlight the effectiveness of using Bayesian optimization for multicomponent materials.
- Takamitsu Ishiyama
- Koki Nozawa
- Kaoru Toko