[16a-K505-1~9] 23.1 Joint Session N "Informatics"

11:15 AM - 11:30 AM JST(2:15 AM - 2:30 AM UTC)

[16a-K505-9] Exploration of Superconducting Hydrides with Explainable AI (XAI)

〇Kazuaki Tokuyama¹, Taichi Masuda¹, Souta Miyamoto¹, Katsuaki Tanabe¹ (1.Kyoto Univ.)

Keywords:

Superconductor,Machine Learning,Hydride

Superconducting hydrides exhibit high critical temperatures under high pressures, making them promising candidates for realizing room-temperature superconductivity. However, conventional binary hydrides typically require pressures on the order of 10² GPa to stabilize in a metallic state. To address this limitation, ternary hydrides have been investigated as a potential solution to reduce the stabilization pressure. In this study, we utilized data-driven approaches and interpretable machine learning models enhanced by XAI (Explainable AI) to efficiently explore ternary superconducting hydride materials and identify promising compositions and their optimal ratios.