Robust Regression for Automatic Fusion Plasma Analysis based on Generative Modeling

TL;DR

This paper introduces a robust regression method for fusion plasma data analysis using generative modeling, improving fitting stability and accuracy over classical methods by estimating the data distribution with machine learning.

Contribution

The paper presents a novel generative modeling approach to fit noisy fusion plasma data, addressing the challenge of unknown data distributions and enhancing fitting performance.

Findings

Generative modeling improves fitting stability.

The method outperforms classical heuristic algorithms.

Enhanced accuracy in temperature and density profile fitting.

Abstract

The first step to realize automatic experimental data analysis for fusion plasma experiments is fitting noisy data of temperature and density spatial profiles, which are obtained routinely. However, it has been difficult to construct algorithms that fit all the data without over- and under-fitting. In this paper, we show that this difficulty originates from the lack of knowledge of the probability distribution that the measurement data follow. We demonstrate the use of a machine learning technique to estimate the data distribution and to construct an optimal generative model. We show that the fitting algorithm based on the generative modeling outperforms classical heuristic methods in terms of the stability as well as the accuracy.