A Prediction Model of the Grid Point Ionospheric TEC
-
摘要: 基于分析时间序列数据的门限控制单元(GRU)神经网络模型,利用电离层TEC网格点历史数据、太阳活动指数、地磁活动指数作为预测因子,提出一种高精度电离层TEC格点预测模型.对全球60个网格点的数据进行了模型预测和对比实验,得到北半球平均相对精度的均值为83.96%,高于南半球的73.60%,表明预测模型在北半球的适应性更好,且中低纬地区的适应性优于高纬地区;预测模型在磁扰动期的平均相对精度的均值比磁平静期平均相对精度的均值高,约1.95%;与基于递归神经网络(RNN)、长短时记忆网络(LSTM)和双向长短时记忆网络(Bi-LSTM)的电离层TEC单站预测模型相比,本文预测模型的均方根误差(RMSE)平均为原来的80.8%.Abstract: A high-precision ionospheric TEC grid point prediction model is established using Gate Recurrent Unit (GRU) neural network model suitable for analyzing time series data. Ionospheric TEC grid point historical data, solar activity index, and geomagnetic activity index are used as inputs of our model. After our in-depth research and analysis, the data of 60 grid points were employed to predict model and do comparative experiments, and the results show that the mean value of average relative accuracy of the northern hemisphere is 83.96%, higher than 73.60% of the southern hemisphere. It presents that the adaptability of the prediction model is better in the northern hemisphere, and especially in the middle and low latitudes rather than in the high latitudes. The second result is that the mean value of the average relative accuracy of the prediction model in magnetic disturbance period is about higher 1.95% higher than that in magnetic quiet period. Finally, we compared the prediction results of several representative models. Compared with the single station prediction model based on RNN, LSTM and Bi-LSTM, the RMSE of this prediction model is reduced to 80.8% on average.
-
Key words:
- Ionosphere /
- Grid point prediction model /
- Gate Recurrent Unit model
-
[1] RADICELLA S M, LEITINGER R, BELEHAKI A, et al. Total electron content-A key parameter in propagation:measurement and use in ionospheric imaging[J]. Ann. Geophys., 2004, 47(2/3):1067-1091 [2] ZHANG Lu. Based on the Time Series, Neural Network, Grey and Combination Forecasting of Ionospheric TEC Forecast Research[D]. Nanjing:Nanjing University of Information Science and Technology, 2012(张禄. 基于时间序列、神经网络、灰色和组合预测对电离层TEC的预测研究[D]. 南京:南京信息工程大学, 2012) [3] WU Wenjun. Study of Ionosphere TEC Prediction Models[D]. Beijing:Graduates School of Chinese Academy of Sciences, 2008(武文俊. 电离层TEC预报模型的研究[D]. 北京:中国科学院研究生院, 2008) [4] KLOBUCHAR J A. Ionospheric time-delay algorithm for single-frequency GPS users[J]. IEEE Trans. Aerosp. Electron. Syst., 1987, 23(3):325-331 [5] DAI Chunli, PING Jinsong. Modeling and prediction of TEC in China region for satellite navigation[C]//2009 15th Asia-Pacific Conference on Communications. Shanghai:IEEE, 2009:310-313 [6] LI Zhigang, CHENG Zongyi, TENG Chugang, et al. A study of prediction models for ionosphere[J]. Chin. J. Geophys., 2007, 50(2):327-337 [7] BILITZA D. International reference ionosphere (1990)[J]. Planet. Space Sci., 1992, 40(4):544 [8] LI Xiuhai, GUO Dazhi. Modeling and prediction of ionospheric total electron content by time series analysis[C]//20102nd International Conference on Advanced Computer Control. Shenyang:IEEE, 2010:375-379 [9] CHEN Peng, YAO Yibin WU Han. TEC prediction of ionosphere based on time series analysis[J]. Geomat. Inform. Sci. Wuhan Univ., 2011, 36(3):267-270(陈鹏, 姚宜斌, 吴寒. 利用时间序列分析预报电离层TEC[J]. 武汉大学学报信息科学版, 2011, 36(3):267-270) [10] HUANG Zhi, YUAN Hong. Ionospheric single-station TEC short-term forecast using RBF neural network[J]. Radio Sci., 2014, 49(4):283-292 [11] ELMUNIM N A, ABDULLAH M, HASBI A M. Improving ionospheric forecasting using statistical method for accurate GPS positioning over Malaysia[C]//2016 International Conference on Advances in Electrical, Electronic and Systems Engineering (ICAEES). Putrajaya:IEEE, 2016:352-355 [12] YUAN Tianjiao, CHEN Yanhong, LIU Siqing, et al. Prediction model for ionospheric total electron content based on deep learning recurrent neural network[J]. Chin. J. Space Sci., 2018, 38(1):48-57 [13] SUN Wenqing, XU Long, HUANG Xin, et al. Forecasting of ionospheric vertical total electron content (TEC) using LSTM networks[C]//2017 International Conference on Machine Learning and Cybernetics (ICMLC). Ningbo:IEEE, 2017:340-344 [14] YAN Yihua, HUANG Xin, ZHANG Weiqiang, et al. Bidirectional LSTM for ionospheric vertical Total Electron Content (TEC) forecasting[C]//2017 IEEE Visual Communications and Image Processing (VCIP). Shenzhen:IEEE, 2017:1-4 [15] SONG Rui, ZHANG Xuemin, CHEN Zhou, et al. Predicting TEC in China based on the neural networks optimized by genetic algorithm[J]. Adv. Space Res., 2018, 62(4):745-759 [16] MUKESH R, SOMA P, KARTHIKEYAN V, et al. Prediction of ionospheric vertical total electron content from GPS data using ordinary Kriging-based surrogate model[J]. Astrophys. Space Sci., 2019, 364(1):15 [17] HOCHREITER S, SCHMIDHUBER, JURGEN. Long Short-Term memory[J]. Neural Comput., 1997, 9(8):1735-1780 [18] , arXiv preprint arXiv:1412.3555, 2014 [19] CLEVERT, DJORK-ARNE, UNTERTHINER T, et al. Fast and accurate deep network learning by Exponential Linear Units (ELUs)[J]. Comput. Sci., 2015, arXiv preprint arXiv:1511.07289, 2015 [20] KINGMA D, BA J. Adam:A method for stochastic optimization[J]. Comput. Sci., 2014, (): [21] HAN Jide, WANG Zushun, WANG Chunqing. Analysis of temporal and spatial change in global ionosphere[J]. J. Geomat., 2012, 37(6):26-29(韩吉德, 王祖顺, 王春青. 全球电离层时空变化特性分析[J]. 测绘地理信息, 2012, 37(6):26-29) [22] LIU Kang, WANG Feng, ZHAI Xu. Statistical analysis and global trend analysis of ionospheric TEC data[J]. Bull. Surv. Mapp., 2013, 1:29-32(刘康, 王枫, 翟旭. 全球电离层TEC数据统计分析与全局趋势分析[J]. 测绘通报, 2013, 1:29-32) [23] TU Jiannan, WAN Weixing, NING Baiqi, et al. Distribution of impulsive electric field in the near earth plasma sheet during storm and non-storm time[J]. Chin. J. Space Sci., 2001, 1:9-16(涂剑南, 万卫星, 宁百齐, 等. 磁扰动和磁静时近地等离子体片中脉冲电场的分布[J]. 空间科学学报, 2001, 1:9-16)
点击查看大图
计量
- 文章访问数: 426
- HTML全文浏览量: 56
- PDF下载量: 41
- 被引次数: 0