Automatic Identification of MHD Modes in Magnetic Fluctuations Spectrograms using Deep Learning Techniques

TL;DR

This paper introduces a deep learning-based software tool that accurately identifies MHD oscillation modes from spectrograms, facilitating faster analysis of large experimental datasets in fusion research.

Contribution

The study develops and trains a CNN-based tool for automatic MHD mode detection in spectrograms, demonstrating high accuracy and practical application in fusion device data analysis.

Findings

Detector AUC score of 0.99 on test data

Effective identification of MHD modes in spectrograms

Potential for mining large experimental databases

Abstract

The control and mitigation of MHD oscillations modes is an open problem in fusion science because they can contribute to the outward particle/energy flux and can drive the device away from ignition conditions. It is then of general interest to extract the mode information from large experimental databases in a fast and reliable way. We present a software tool based on Deep Learning that can identify these oscillations modes taking Mirnov coil spectrograms as input data. It uses Convolutional Neural Networks that we trained with manually annotated spectrograms from the TJ-II stellarator database. We have tested several detector architectures, resultingin a detector AUC score of 0.99 on the test set. Finally, it is applied to find MHD modes in our spectrograms to show how this new software tool can be used to mine other databases.