Deep learning model for predicting the spatial distribution of binding energy from atomic configurations

Abstract Understanding plasma-material interaction is crucial for achieving steady-state operation of magnetic confinement fusion devices. Kinetic Monte Carlo (kMC) simulation is a powerful tool for investigating the motion of atoms in the plasma facing materials under the influence of this interact...

Full description

Saved in:
Bibliographic Details
Published inJapanese Journal of Applied Physics Vol. 63; no. 9; pp. 9 - 16
Main Authors Saito, Seiki, Sato, Shingo, Nakamura, Hiroaki, Takahashi, Chako, Sawada, Keiji, Hoshino, Kazuo, Kobayashi, Masahiro, Hasuo, Masahiro
Format Journal Article
LanguageEnglish
Published Tokyo IOP Publishing 04.09.2024
Japanese Journal of Applied Physics
Subjects
Binding energy
Deep learning
Energy distribution
kMC
molecular dynamics
numerical simulation
plasma-material interaction
Spatial distribution
Steady state models
Online AccessGet full text

Cover

More Information
Summary:Abstract Understanding plasma-material interaction is crucial for achieving steady-state operation of magnetic confinement fusion devices. Kinetic Monte Carlo (kMC) simulation is a powerful tool for investigating the motion of atoms in the plasma facing materials under the influence of this interaction. To predict trapping sites and migration energies necessary for kMC simulations, we developed a deep learning model based on pix2pix for predicting the spatial distribution of binding energy. Results show that the model can reproduce spatial distributions similar to the true values. However, larger errors occur in regions with steep value gradients.
Bibliography:JJAP-S1104031.R1
ISSN:0021-4922
1347-4065
DOI:10.35848/1347-4065/ad6e8e