[2E01-04] Fuel Research with Data Science and Machine Learning, Fast Reactor Recycle

[2E02] New Developments in Nuclear Fuel Research through Integration with Data Science

(9) Development of neural network potential of UO2

*Kenji Konashi¹, Nobuhiko Kato², Kazuki Mori², Ken Kurosaki³ (1. Tohoku Univ., 2. CTC, 3. Kyoto Univ.)

Keywords:Neural network potential, machine learning, nuclear fuel, molecular dynamics

Neural network potential for UO₂ has been developed using artificial intelligence (AI)technology. The elastic modulas and two-body correlation function were calculated by molecular dynamics (MD) method with the potential.