Deep Learning for Plasma Tomography and Disruption Prediction from Bolometer Data
This work addresses data processing challenges in fusion energy research, but it is incremental as it applies standard deep learning methods to a specific domain.
The paper tackles plasma radiation profile reconstruction and disruption prediction in fusion devices using CNNs and RNNs on bolometer data from JET, demonstrating applicability to other fusion systems.
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.