[22p-M206-1~16] 23.1 Joint Session N "Informatics"

△ [22p-M206-10] Multimodal AI for Virtual Screening of Complex Composite Materials

〇Shun Muroga¹, Yasuaki Miki¹, Takashi Honda², Hiroshi Morita¹, Toshiya Okazaki¹, Kenji Hata¹ (1.AIST, 2.ADMAT)

Keywords:multimodal AI, materials informatics, deep learning

Conventional materials and process informatics techniques are limited for chemical compounds or inorganic materials because they require precise definition of structures to generate descriptors, which leads to the difficulty in the fields of complex composite materials. In this study, we propose a novel concept of multimodal AI which can be applied to the field of material science. In this conference I would like to talk the overview of our concept of multimodal AI for materials and results in the case of composite materials.