Bayesian neural network for plasma equilibria in the Korea Superconducting Tokamak Advanced Research

TL;DR

This paper proposes a Bayesian neural network approach to model plasma equilibria in the Korea Superconducting Tokamak Advanced Research, aiming to incorporate physical theories and quantify uncertainty in deep learning models for fusion plasma control.

Contribution

It introduces a Bayesian neural network framework that integrates physical theories and provides uncertainty quantification for plasma equilibrium modeling.

Findings

Enhanced uncertainty estimation in plasma modeling

Improved integration of physical theories into deep learning

Potential for more reliable plasma control strategies

Abstract

Fusion-graded plasmas are one of the physically complex systems, resulting in continuous establishment of plasma theories for unclarified physical phenomena in order to thoroughly control nuclear fusion reactors. Deep learning has drawn vast attention to this field of controlled fusion plasma to link physical phenomena with control-relevant parameters without a deepened understanding about plasma theories. Albeit, quantifying the uncertainty of deep learning models has been constantly requested due to their fundamental shortage of physical understanding. Thus, a concept of a reliable deep learning model to be able to present their probability distributions is raised as well as a method to inculcate physical theories in the model is also concerned.