组合模型的电离层总电子短期预报研究Research on combined model in short term ionospheric total electron prediction
王建敏,唐彦,吕楠,李特
摘要(Abstract):
针对电离层总电子含量(TEC)是受到众多影响因素的非平稳性、非线性时间序列的问题,该文提出一种基于小波分解与埃尔曼(Elman)神经网络模型和差分自回归移动平均(ARIMA)模型组合的方法。利用db4小波对电离层TEC样本序列分解得到低频信息和高频信息,对高频信息采用ARIMA模型进行预报,对低频信息采用Elman神经网络模型进行预报,将ARIMA模型和Elman神经网络模型的预报值进行重构,从而得到电离层TEC的预测值。实验表明,组合模型在电离层平静期和活跃期预报的均方根误差分别为0.83、1.08 TECu,残差小于1 TECu的比例分别为80.28%、68.00%,较单一模型有了大幅的提升。
关键词(KeyWords): 电离层;总电子含量;小波分解;埃尔曼神经网络;差分自回归移动平均模型
基金项目(Foundation): 国家自然科学基金项目(41474020)
作者(Author): 王建敏,唐彦,吕楠,李特
DOI: 10.16251/j.cnki.1009-2307.2022.04.005
参考文献(References):
- [1]王喜江,边少锋,李子申,等.利用半参数核估计法预报全球电离层总电子含量[J].地球物理学报,2020,63(4):1271-1281.(WANG Xijiang,BIAN Shaofeng,LI Zishen,et al.Prediction of global ionospheric TECusing the semiparametric kernel estimation method[J].Chinese Journal of Geophysics,2020,63(4):1271-1281.)
- [2]王宁波,袁运斌,李子申,等.不同NeQuick电离层模型参数的应用精度分析[J].测绘学报,2017,46(4):421-429.(WANG Ningbo,YUAN Yunbin,LI Zishen,et al.Performance analysis of different NeQuick ionospheric model parameters[J].Acta Geodaetica et Cartographica Sinica,2017,46(4):421-429.)
- [3]王建敏,黄佳鹏,祝会忠,等.电离层TEC预报模型的卡尔曼滤波改进方法[J].导航定位学报,2018,6(1):27-33.(WANG Jianmin,HUANG Jiapeng,ZHUHuizhong,et al.Improvement of forecasting models of ionospheric TEC by Kalman filter[J].Journal of Navigation and Positioning,2018,6(1):27-33.)
- [4]安家春,宁新国,王泽民,等.利用球冠谐函数和时间序列分析预报南极地区电离层[J].武汉大学学报(信息科学版),2015,40(5):677-681.(AN Jiachun,NINGXinguo,WANG Zemin,et al.Antarctic ionospheric prediction based on spherical cap harmonic analysis and time series analysis[J].Geomatics and Information Science of Wuhan University,2015,40(5):677-681.)
- [5]TARIKU Y A.TEC prediction performance of the IRI-2012model over Ethiopia during the rising phase of solar cycle 24 (2009-2011)[J].Earth,Planets and Space,2015,67:140.
- [6]田睿,董绪荣.小波分解与Prophet框架融合的电离层VTEC预报模型[J].系统工程与电子技术,2021,43(3):610-622.(TIAN Rui,DONG Xurong.Ionosphere VTEC prediction model fused with wavelet decomposition and Prophet framework[J].Systems Engineering and Electronics,2021,43(3):610-622.)
- [7]LI Shuhui,PENG Junhuan.Variability of ionospheric TEC and the performance of the IRI-2012model at the BJFS station,China[J].Acta Geophysica,2016,64(5):1970-1987.
- [8]汤俊,高鑫.贝叶斯正则化的Elman神经网络电离层TEC预报模型[J].大地测量与地球动力学,2020,40,(8):799-805.(TANG Jun,GAO Xin.Prediction models of ionospheric TEC by Elman neural network with Bayesian regularization[J].Journal of Geodesy and Geodynamics,2020,40,(8):799-805.)
- [9]冯炜,张传定,吴星,等.全球电离层TEC的轮胎调和分析与预报[J].测绘学报,2018,47(5):600-610.(FENG Wei,ZHANG Chuanding,WU Xing,et al.Torus harmonic analysis and prediction of global ionospheric TEC[J].Acta Geodaetica et Cartographica Sinica,2018,47(5):600-610.)
- [10]张小红,任晓东,吴风波,等.自回归移动平均模型的电离层总电子含量短期预报[J].测绘学报,2014,43(2):118-124.(ZHANG Xiaohong,REN Xiaodong,WUFengbo,et al.Short-term TEC prediction of ionosphere based on ARIMA model[J].Acta Geodaetica et Cartographica Sinica,2014,43(2):118-124.)
- [11]刘立龙,陈军,黄良珂,等.基于小波-ARIMA电离层短期总电子含量预报[J].桂林理工大学学报,2016,36(2):294-299.(LIU Lilong,CHEN Jun,HUANGLiangke,et al.TEC forecast of short-term ionosphere based on wavelet-ARIMA[J].Journal of Guilin University of Technology,2016,36(2):294-299.)
- [12]田祥雨,刘立龙,杨可可,等.BP神经网络和ARIMA模型的变权组合电离层TEC预报[J].桂林理工大学学报,2019,39(4):899-904.(TIAN Xiangyu,LIULilong,YANG Keke,et al.Ionospheric TEC prediction based on variable weight combination of BP neural network and ARIMA model[J].Journal of Guilin University of Technology,2019,39(4):899-904.)
- [13]刘立龙,陈雨田,黎峻宇,等.活跃期区域电离层总电子短期预报及适用性分析[J].武汉大学学报(信息科学版),2019,44(12):1757-1764.(LIU Lilong,CHENYutian,LI Junyu,et al.Short-term prediction and applicability analysis of regional ionospheric total electron content in active period[J].Geomatics and Information Science of Wuhan University,2019,44(12):1757-1764.)
- [14]王建敏,黄佳鹏,祝会忠,等.电离层总电子数预报方法研究[J].测绘科学,2016,41(12):47-52.(WANGJianmin,HUANG Jiapeng,ZHU Huizhong,et al.Study of the ionosphere TEC forecasting method[J].Science of Surveying and Mapping,2016,41(12):47-52.)
- [15]鲍亚东,刘长建,柴洪洲.小波分解改进电离层VTEC时间序列预报模型[J].大地测量与地球动力学,2015,35(5):784-787.(BAO Yadong,LIU Changjian,CHAI Hongzhou.Time series prediction model of ionospheric VTEC improved by wavelet decomposition[J].Journal of Geodesy and Geodynamics,2015,35(5):784-787.)