Using convolutional neural networks to detect edge localized modes in DIII-D from Doppler backscattering measurements.
| Autor: | Teo NQX; Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore 138632.; School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore 637371., Hall-Chen VH; Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore 138632., Barada K; Department of Physics and Astronomy, University of California, Los Angeles, California 90095, USA., Ng RJH; Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore 138632., Gu L; AIP, RIKEN, Tokyo 103-0027, Japan., Yeoh AK; Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore 138632.; Department of Physics, University of Oxford, Oxford OX1 3PU, United Kingdom., Pratt QT; Department of Physics and Astronomy, University of California, Los Angeles, California 90095, USA., Garbet X; School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore 637371., Rhodes TL; Department of Physics and Astronomy, University of California, Los Angeles, California 90095, USA. |
|---|---|
| Jazyk: | angličtina |
| Zdroj: | The Review of scientific instruments [Rev Sci Instrum] 2024 Jul 01; Vol. 95 (7). |
| DOI: | 10.1063/5.0215748 |
| Abstrakt: | In H-mode tokamak plasmas, the plasma is sometimes ejected beyond the edge transport barrier. These events are known as edge localized modes (ELMs). ELMs cause a loss of energy and damage the vessel walls. Understanding the physics of ELMs, and by extension, how to detect and mitigate them, is an important challenge. In this paper, we focus on two diagnostic methods-deuterium-alpha (Dα) spectroscopy and Doppler backscattering (DBS). The former detects ELMs by measuring Balmer alpha emission, while the latter uses microwave radiation to probe the plasma. DBS has the advantages of having a higher temporal resolution and robustness to damage. These advantages of DBS diagnostic may be beneficial for future operational tokamaks, and thus, data processing techniques for DBS should be developed in preparation. In sight of this, we explore the training of neural networks to detect ELMs from DBS data, using Dα data as the ground truth. With shots found in the DIII-D database, the model is trained to classify each time step based on the occurrence of an ELM event. The results are promising. When tested on shots similar to those used for training, the model is capable of consistently achieving a high f1-score of 0.93. This score is a performance metric for imbalanced datasets that ranges between 0 and 1. We evaluate the performance of our neural network on a variety of ELMs in different high confinement regimes (grassy ELM, RMP mitigated, and wide-pedestal), finding broad applicability. Beyond ELMs, our work demonstrates the wider feasibility of applying neural networks to data from DBS diagnostic. (© 2024 Author(s). Published under an exclusive license by AIP Publishing.) |
| Databáze: | MEDLINE |
| Externí odkaz: |
|