Estimation of 2D profile dynamics of electrostatic potential fluctuations using multi-scale deep learning

被引:3
|
作者
Jajima, Yuki [1 ]
Sasaki, Makoto [1 ]
Ishikawa, Ryohtaroh T. [2 ]
Nakata, Motoki [2 ,3 ]
Kobayashi, Tatsuya [2 ]
Kawachi, Yuichi [4 ]
Arakawa, Hiroyuki [5 ]
机构
[1] Nihon Univ, Coll Ind Technol, Narashino 2758575, Japan
[2] Natl Inst Fus Sci, Toki 5095292, Japan
[3] Japan Sci & Technol Agcy, PRESTO, Kawaguchi 3320012, Japan
[4] Kyoto Inst Technol, Dept Elect, Sakyo 6068585, Japan
[5] Kyushu Univ, Fac Med Sci, Fukuoka 8128582, Japan
关键词
plasma turbulence; particle transport; deep learning; TURBULENCE;
D O I
10.1088/1361-6587/acff7f
中图分类号
O35 [流体力学]; O53 [等离子体物理学];
学科分类号
070204 ; 080103 ; 080704 ;
摘要
Dynamics in magnetically confined plasmas are dominated by turbulence driven by spatial inhomogeneities in density and temperature. Simultaneous measurement of velocity field and density fluctuations is necessary to observe the particle transport, but the measurement of the velocity field fluctuations is often challenging. Here, we propose a method to estimation velocity field fluctuations from density fluctuations by using plasma turbulence simulations and a deep technique learning. In order to take multi-scale characteristics into account, the several number of spatial filters are used in the convolutional neural network. The velocity field fluctuations are successfully predicted, and the particle transport estimated from the predicted velocity field fluctuations is within 93.1% accuracy. The deep learning could be used for the prediction of physical variables which are difficult to be measured.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] 2D deblending using the multi-scale shaping scheme
    Li, Qun
    Ban, Xingan
    Gong, Renbin
    Li, Jinnuo
    Ge, Qiang
    Zu, Shaohuan
    JOURNAL OF APPLIED GEOPHYSICS, 2018, 148 : 44 - 54
  • [2] Deep Multi-Scale Feature Learning for Defocus Blur Estimation
    Karaali, Ali
    Harte, Naomi
    Jung, Claudio R.
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 : 1097 - 1106
  • [3] Improving Feature Learning in Remote Sensing Images Using an Integrated Deep Multi-Scale 3D/2D Convolutional Network
    Tinega, Haron C. C.
    Chen, Enqing
    Nyasaka, Divinah O. O.
    REMOTE SENSING, 2023, 15 (13)
  • [4] Multi-Scale Compositionality: Identifying the Compositional Structures of Social Dynamics Using Deep Learning
    Peng, Huan-Kai
    Marculescu, Radu
    PLOS ONE, 2015, 10 (04):
  • [5] 2D medical image segmentation via learning multi-scale contextual dependencies
    Pang, Shuchao
    Du, Anan
    Yu, Zhenmei
    Orgun, Mehmet A.
    METHODS, 2022, 202 : 40 - 53
  • [6] Multi-scale 2D Representation Learning for weakly-supervised moment retrieval
    Li, Ding
    Wu, Rui
    Tang, Yongqiang
    Zhang, Zhizhong
    Zhang, Wensheng
    2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 8616 - 8623
  • [7] Skeleton-aware Multi-scale Heatmap Regression for 2D Hand Pose Estimation
    Kourbane, Ikram
    Genc, Yakup
    Informatica (Slovenia), 2021, 45 (04): : 593 - 604
  • [8] Skeleton-aware Multi-scale Heatmap Regression for 2D Hand Pose Estimation
    Kourbane, Ikram
    Genc, Yakup
    INFORMATICA-AN INTERNATIONAL JOURNAL OF COMPUTING AND INFORMATICS, 2021, 45 (04): : 593 - 604
  • [9] Deep Optical Flow Estimation Via Multi-Scale Correspondence Structure Learning
    Zhao, Shanshan
    Li, Xi
    Bourahla, Omar El Farouk
    PROCEEDINGS OF THE TWENTY-SIXTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 3490 - 3496
  • [10] Multi-scale 2D tracking of articulated objects using hierarchical spring systems
    Artner, Nicole M.
    Ion, Adrian
    Kropatsch, Walter G.
    PATTERN RECOGNITION, 2011, 44 (09) : 1969 - 1979