[15a-A21-1~11] 15.4 III-V-group nitride crystals

△ [15a-A21-7] Rapid prediction of solution flow by machine learning
in AlN solution growth

〇Nobuhiko Kokubo¹, Yosuke Tsunooka¹, Shunta Harada¹, Miho Tagawa¹, Toru Ujihara¹ (1.Nagoya Univ.)

Keywords:machine learning, AlN, fluid simulation

Fluid flow is one of the most important parameters for crystal growth. Computational fluid dynamics (CFD) simulation is powerful method to know the solution flow distribution. In order to optimize the growth configuration for the suitable solution flow, it is necessary to exhaustively simulate various kinds of configurations. However, the CFD simulations take a plenty of time. In this study, we applied the sparse modelling which is a variety of machine learning. Keeping AlN solution growth in mind, We performed the rapid prediction of solution flow by using the small number of simulation results.