[S1] S1 New Materials Science on Nanoscale Structures and Functions at Crystal Interface II

3:35 PM - 3:55 PM JST(6:35 AM - 6:55 AM UTC)

[S1.11] Prediction of Oxygen-Vacancy Structures and Formation Energies via a Machine-Learning Potential

○Atsushi Takigawa^1,2, Shin Kiyohara², Yu Kumagai² (1. Graduate School of Engineering, Tohoku University, 2. Institute for Materials Research, Tohoku University)

Keywords:

Machine-Learning Potential,Oxygen Vacancy,Defect Formation Energy

Oxygen vacancies are key point defects in metal oxides. We fine-tuned the universal machine-learning potential SevenNet-Omni on neutral oxygen-vacancy relaxation trajectories in 937 oxides, predicting formation energies and relaxed structures from one potential, surpassing conventional regression.