[10p-Z23-1~16] 15.6 Group IV Compound Semiconductors (SiC)

▲ [10p-Z23-1] Solution growth of 150 mm SiC under the guidance of machine learning

〇Wancheng YU¹, Can ZHU¹, Yosuke TSUNOOKA², Wei HUANG², Yifan DANG², Shunta HARADA^1,2, Miho TAGAWA^1,2, Toru UJIHARA^1,2,3 (1.IMaSS, Nagoya Univ., 2.Nagoya Univ., 3.GaN-OIL, AIST)

Keywords:Machine learning, Solution growth, SiC

In this paper, 150 mm (6-inch) SiC crystals was fabricated by TSSG technique with the guidance of machine learning. The machine learning technique was adopted to find out the optimal configuration from all possible conditions for crystal growth. By applying the optimal results given by the machine learning, 150 mm 4H-SiC crystal was grown in reality by top-seed solution growth method.Commercial 150 mm 4H-SiC substrates with 4 ° off [0001]-oriented were used as seed crystals.The SiC samples shows uniform step flow surface morphology.Therefore, the machine learning technique represents an innovative and attractive strategy in the development of crystal growth.