Deep Learning for Plasma Tomography and Disruption Prediction from Bolometer Data

TL;DR

This paper explores the application of deep learning techniques, specifically CNNs and RNNs, to analyze fusion diagnostic data for plasma tomography and disruption prediction at JET, demonstrating their potential for broader use in fusion research.

Contribution

It introduces CNN-based plasma radiation profile reconstruction and discusses RNN-based disruption prediction using fusion diagnostic data.

Findings

CNNs successfully reconstruct plasma radiation profiles.

RNNs show potential for disruption prediction.

Approaches are applicable to other fusion devices.

Abstract

The use of deep learning is facilitating a wide range of data processing tasks in many areas. The analysis of fusion data is no exception, since there is a need to process large amounts of data collected from the diagnostic systems attached to a fusion device. Fusion data involves images and time series, and are a natural candidate for the use of convolutional and recurrent neural networks. In this work, we describe how CNNs can be used to reconstruct the plasma radiation profile, and we discuss the potential of using RNNs for disruption prediction based on the same input data. Both approaches have been applied at JET using data from a multi-channel diagnostic system. Similar approaches can be applied to other fusion devices and diagnostics.