[20a-A21-1~10] 23.1 Joint Session N "Informatics"

9:00 AM - 9:15 AM JST(12:00 AM - 12:15 AM UTC)

[20a-A21-1] Validation experiments of machine learning for Eu valence in phosphor materials

〇Yukinori Koyama¹, Yukako Kohriki¹, Masamichi Harada¹, Naoto Hirosaki¹, Takashi Takeda¹ (1.NIMS)

Keywords:

phosphor,machine learning,validation experiment

Europium takes on divalent and trivalent states in the phosphor host crystal. The valence of europium can change depending on the synthesis conditions, but for most hosts, only one of the valence states is obtained. Therefore, it is necessary to select hosts that can obtain the desired valence. Therefore, we have constructed a machine learning model to predict the valence of europium in the hosts. In this paper, we report on the discovery of novel Eu²⁺-activated phosphors by conducting validation experiments of the machine-learning model we developed.