Using Convolutional Neural Networks to detect Edge Localized Modes in DIII-D from Doppler Backscattering measurements
Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)（高性能计算研究所，科学与技术研究局）；School of Physical and Mathematical Sciences, Nanyang Technological University（南洋理工大学物理与数学科学学院）；Department of Physics and Astronomy, University of California, Los Angeles（加州大学洛杉矶分校物理与天文学系）；AIP, RIKEN（理化学研究所应用物理部）；Department of Physics, University of Oxford（牛津大学物理系）
N. Q. X. Teo, V. H. Hall-Chen, K. Barada, R. J. H. Ng, L. Gu, A. K. Yeoh, Q. T. Pratt, X. Garbet, T. L. Rhodes
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 $\unicode{x2013}$ D-alpha 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 advantage of having higher temporal resolution and robustness to damage. These advantages of DBS diagnostics 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 D-alpha 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 $\unicode{x2013}$ grasssy, suppressed, and wide pedestal $\unicode{x2013}$ finding broad applicability. Beyond ELMs, our work demonstrates the wider feasibility of applying neural networks to data from DBS diagnostics.
Forecasting the first Edge Localized Mode (ELM) after LH-transition with a neural network trained on Doppler Backscattering data from DIII-D
Agency for Science, Technology and Research (A*STAR)（科学技术研究局）；Nanyang Technological University（南洋理工大学）；University of California, Los Angeles（加州大学洛杉矶分校）；Tohoku University（东北大学）
A Doppler backscattering diagnostic for the EXL-50U spherical tokamak: plasma considerations and preliminary quasioptical design
A*STAR Research Entities（新加坡科学研究局）；Imperial College London（帝国理工学院）；Nanyang Technological University（南洋理工大学）；UCLA（加州大学洛杉矶分校）；ENN Science & Technology Development Co., Ltd（新奥科技发展有限公司）
Conceptual study on using Doppler backscattering to measure magnetic pitch angle in tokamak plasmas
Future Energy Acceleration and Translation Programme, Agency of Science, Technology and Research (A*STAR)（未来能源加速与转化计划，科学与技术研究局）；Department of Physics, University of Oxford（牛津大学物理系）；Department of Physics and Astronomy, University of California, Los Angeles（加州大学洛杉矶分校物理与天文学系）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）；Department of Physics, National University of Singapore（新加坡国立大学物理系）；Commonwealth Fusion Systems（联邦聚变系统）；Princeton Plasma Physics Laboratory（普林斯顿等离子体物理实验室）；Rudolf Peierls Centre for Theoretical Physics, University of Oxford（牛津大学鲁道夫·佩尔斯理论物理中心）
Beam-Tracing-Based Quantitative Reconstruction of Density Fluctuations in QUEST Using Doppler Backscattering
Research Institute for Applied Mechanics, Kyushu University（九州大学应用力学研究所）；National Institute for Fusion Science（国立研究开发法人核融合科学研究所）；Future Energy Acceleration & Translation (FEAT), Agency for Science, Technology and Research (A*STAR)（科学技术研究局未来能源加速与转化中心）
Comparison of DBS measurements of turbulence spectra by vertical-displacement and poloidal-angle scans using the Scotty synthetic diagnostic
Agency for Science, Technology and Research (A*STAR)（科学与技术研究局）；Nanyang Technological University（南洋理工大学）；University of California, Los Angeles (UCLA)（加州大学洛杉矶分校）
