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

9:30 AM - 9:45 AM JST(12:30 AM - 12:45 AM UTC)

[20a-A21-3] Efficient Material Exploration for Anion Exchange Membranes using Combined Materials Map-Supervised Machine Learning

〇(D)YinKan Phua¹, Tsuyohiko Fujigaya^1,2,3, Koichiro Kato^1,2,4 (1.Grad. Sch. of Eng., Kyushu Univ., 2.CMS, Kyushu Univ., 3.I2CNER, Kyushu Univ., 4.RIIT, Kyushu Univ.)

Keywords:

machine learning,fuel cell,polymer

Anion exchange membranes (AEMs) are essential components of fuel cells for realizing a hydrogen society. However, the performance of AEMs remains inadequate. In this study, we aimed to develop an efficient exploration method for high anion conductivity structures of AEMs by combining the usage of a two-dimensional map obtained via unsupervised machine learning (ML) with a supervised ML model. The two-dimensional map was used as material design guidelines to explore promising AEMs, with the anion conductivity of newly designed AEMs predicted by a supervised ML model. This integrated operation of material map and supervised ML model realized a more targeted and efficient material exploration method.