Volume 38 Issue 1
Jan.  2018
Turn off MathJax
Article Contents
YUAN Tianjiao, CHEN Yanhong, LIU Siqing, GONG Jiancun. Prediction Model for Ionospheric Total Electron Content Based on Deep Learning Recurrent Neural Networkormalsize[J]. Journal of Space Science, 2018, 38(1): 48-57. doi: 10.11728/cjss2018.01.048
Citation: YUAN Tianjiao, CHEN Yanhong, LIU Siqing, GONG Jiancun. Prediction Model for Ionospheric Total Electron Content Based on Deep Learning Recurrent Neural Networkormalsize[J]. Journal of Space Science, 2018, 38(1): 48-57. doi: 10.11728/cjss2018.01.048

Prediction Model for Ionospheric Total Electron Content Based on Deep Learning Recurrent Neural Networkormalsize

doi: 10.11728/cjss2018.01.048
  • Received Date: 2017-03-18
  • Rev Recd Date: 2017-09-01
  • Publish Date: 2018-01-15
  • A 24h ahead forecasting model for ionospheric Total Electron Content (TEC) at Beijing station is established based on the deep learning Recurrent Neural Network (RNN) for the first time. The model implementation requires solar 10.7cm flux index, geomagnetic index ap, grid map of TEC, solar wind speed and the southward components of interplanetary magnetic field. The predicting results for Beijing station (40°N, 115°E) show that the Root Mean Square Error (RMSE) of the disturbed ionosphere TEC predicted by RNN model is lower than that of BPNN (Back Propagation Neural Network) model by 0.49~1.46TECU. The forecasting accuracy of ionospheric positive storm by RNN model is increased by 16.8% with solar wind parameters. Furthermore, the RMSE of RNN model of 31 strong TEC storms in 2001 and 2015 are less than those of BPNN model by 0.2TECU, and the RMSE of RNN model is decreased by 0.36~0.47TECU as solar wind parameters are added. The results indicate that RNN model is more reliable than BP model for short-term forecasting of TEC. Moreover, the addition of interplanetary solar wind parameters are helpful for predicting TEC positive storm.

     

  • loading
  • [1]
    LI Zhigang, CHENG Zongyi, FENG Chugang, et al. A study of prediction models for ionosphere[J]. Chin. J. Geophys., 2007, 50(2):327-337 (李志刚, 程宗颐, 冯初刚, 等. 电离层预报模型研究[J]. 地球物理学报, 2007, 50(2):327-337)
    [2]
    CHEN Yanhong, XUE Bingsen, LI Libin. Forecasting of ionospheric critical frequency using neural networks[J]. Chin. J. Space Sci., 2005, 25(2):99-103 (陈艳红, 薛炳森, 李利斌. 利用神经网络预报电离层f0F2*[J]. 空间科学学报, 2005, 25(2):99-103)
    [3]
    GAO Qing, LIU Libo, ZHAO Biqiang, et al. A prediction method for midlatitude ionospheric storms at a single station based on modified Kp[J]. Progr. Geophys., 2009, 24(6):1943-1950 (高琴, 刘立波, 赵必强, 等. 基于修正Kp指数的中纬区单站电离层暴预报方法研究[J]. 地球物理学进展, 2009, 24(6):1943-1950)
    [4]
    HUANG Z, YUAN H. Ionospheric single-station TEC short-term forecast using RBF neural network[J]. Radio Sci., 2014, 49(4):283-292
    [5]
    BORRIES C, BERDERMANN J, JAKOWSKI N, et al. Ionospheric storms-a challenge for empirical forecast of the total electron content[J]. J. Geophys. Res., 2015, 120(4):3175-3186
    [6]
    SARMA K K, MITRA A. A class of recurrent neural network (RNN) architectures with SOM for estimating MIMO channels[C]//Advances in Computing and Communications. Berlin: Springer, 2011:512-521
    [7]
    NISHIOKA M, MARUYAMA T, TSUGAWA T, et al. Forecast model of ionospheric total electron content over Japan using a machine learning technique[C]//Japan Geoscience Union Meeting, 2016
    [8]
    KOURIS S S, POLIMERIS K V, CANDER L R. Specifications of TEC variability[J]. Adv. Space Res., 2006, 37(5):983-1004
    [9]
    KOURIS S. Thresholds of TEC variability describing the plasmaspheric disturbed state[J]. Acta Geophys., 2008, 56(2):408-416
    [10]
    NAKAMURA M I, MARUYAMA T, SHIDAMA Y. Using a neural network to make operational forecasts of ionospheric variations and storms at Kokubunji, Japan[J]. Earth, Planets Space, 2007, 59(12):1231-1239
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article Views(1157) PDF Downloads(1084) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return