【International Papers】Machine-Learned Fermi Level Prediction of Solution-Processed Ultrawide-Bandgap Amorphous Gallium Oxide (a-Ga₂Oₓ)

      The Fermi level (E_F) relative position to the conduction band minimum is a crucial consideration for controlling electrical conductivity and semiconductor device performance in thin-film transistors, sensors, and photodetectors. Experiment complexity and expensive material resources for predicting E_F via an experimental approach render a machine learning (ML) approach to be more appropriate. This work presents ML-assisted E_F prediction of solution-processed ultrawide-bandgap (UWB) amorphous gallium oxide (a-Ga₂O_x). Three regression models─kernel ridge regression, support vector regression, and random forest regression─were trained with experimental features including the film thickness, baking temperature, and gas environment during solution deposition of the a-Ga₂O_x film. The results show that ML models can be used to predict E_F of the UWB a-Ga₂O_x film and also identify optimized fabrication parameters to achieve the optimized E_F. Moreover, the ML approach can significantly accelerate the fabrication of semiconducting UWB a-Ga₂O_x-based material for future device applications. This work is a big step toward rapid and cost-effective optimization methods for developing UWB a-Ga₂O_x-based devices.

Paper Link：https://pubs.acs.org/doi/abs/10.1021/acsaelm.2c01013