基于深度学习递归神经网络的电离层总电子含量经验预报模型
Prediction Model for Ionospheric Total Electron Content Based on Deep Learning Recurrent Neural Network
查看参考文献10篇
文摘
|
利用行星际太阳风参数与太阳活动指数、地磁活动指数、电离层总电子含量格点化地图数据,首次基于一种能处理时间序列的深度学习递归神经网络(Recurrent Neural Network, RNN),建立提前24h的单站电离层TEC预报模型.对北京站(40°N,115°E)的预测结果显示,RNN对扰动电离层的预测误差低于反向传播神经网络(Back Propagation Neural Network, BPNN) 0.49~1.46 TECU,将太阳风参数加入预报因子模型后对电离层正暴预测准确率的提升可达16.8%. RNN对2001和2015年31个强电离层暴预报的均方根误差比BPNN低0.2 TECU,将太阳风参数加入RNN模型可使31个事件的平均预报误差降低0.36~0.47TECU.研究结果表明深度递归神经网络比BPNN更适用于电离层TEC的短期预报,且在预报因子中加入太阳风数据对电离层正暴的预报效果有明显改善. |
其他语种文摘
|
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 10.7 cm 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 0.49~1.46 TECU. 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 0.2 TECU, 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. |
来源
|
空间科学学报
,2018,38(1):48-57 【核心库】
|
DOI
|
10.11728/cjss2018.01.048
|
关键词
|
电离层暴
;
TEC
;
预报
;
递归神经网络
;
太阳风参数
|
地址
|
1.
中国科学院国家空间科学中心, 北京, 100190
2.
中国科学院大学, 北京, 100049
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
0254-6124 |
学科
|
地球物理学 |
基金
|
国家自然科学基金面上项目
;
国家重点研发计划项目共同资助
|
文献收藏号
|
CSCD:6154934
|
参考文献 共
10
共1页
|
1.
李志刚. 电离层预报模型研究.
地球物理学报,2007,50(2):327-337
|
被引
44
次
|
|
|
|
2.
陈艳红. 利用神经网络预报电离层f0F2.
空间科学学报,2005,25(2):99-103
|
被引
11
次
|
|
|
|
3.
高琴. 基于修正K_p指数的中纬区单站电离层暴预报方法研究.
地球物理学进展,2009,24(6):1943-1950
|
被引
3
次
|
|
|
|
4.
Huang Z. Ionospheric single-station TEC short-term forecast using RBF neural network.
Radio Sci,2014,49(4):283-292
|
被引
15
次
|
|
|
|
5.
Borries C. Ionospheric storms-a challenge for empirical forecast of the total electron content.
J. Geophys. Res,2015,120(4):3175-3186
|
被引
1
次
|
|
|
|
6.
Sarma K K. A class of recurrent neural network (RNN) architectures with SOM for estimating MI-MO channels.
Advances in Computing and Communications,2011:512-521
|
被引
1
次
|
|
|
|
7.
Nishioka M. Forecast model of ionospheric total electron content over Japan using a machine learning technique.
Japan Geoscience Union Meeting,2016
|
被引
1
次
|
|
|
|
8.
Kouris S S. Specifications of TEC variability.
Adv. Space Res,2006,37(5):983-1004
|
被引
5
次
|
|
|
|
9.
Kouris S. Thresholds of TEC variability describing the plasmaspheric disturbed state.
Acta Geophys,2008,56(2):408-416
|
被引
3
次
|
|
|
|
10.
Nakamura M I. Using a neural network to make operational forecasts of ionospheric variations and storms at Kokubunji,Japan.
Earth, Planets Space,2007,59(12):1231-1239
|
被引
3
次
|
|
|
|
|