[8p-P11-1~13] 23.1 Joint Session N "Informatics"

[8p-P11-7] Machine Learning for High-Performance GaN-HEMTs: Optimizing amorphous SiN Thin Film Deposition

〇Sotaro Kuribayashi¹, Kenji Homma¹, Akito Maruo¹, Hiroyuki Higuchi¹, Hideyuki Jippo¹, Atsushi Yamada¹, Toshihiro Ohki¹ (1.Fujitsu Limited)

Keywords:

materials Informatics,causal discovery,amorphous SiN

Machine learning-based material optimization is often performed as a black box process, making it difficult to explain the rationale behind the optimized process conditions. In this study, the amorphous silicon nitride (a-SiN) deposition parameters for an optimal GaN high electron mobility transistor device were determined by also considering the interpretability by correlation analysis and causal discovery.