| 19 | 0 | 0 |
 Reads |
 Downloads |
 Citas |
The ionospheric Es layer shielding frequency (fbEs) is a key parameter affecting the propagation of radio waves. The accurate prediction of fbEs has important application value in the fields of communication and navigation. In this paper, a prediction method based on Transformer deep learning model is proposed to improve the accuracy of the traditional prediction model for fbEs. A model with historical fbEs observation data and auxiliary parameters such as solar activity index as input and fbEs sequence in the next 72 hours as output is constructed, and the fbEs in Beijing, Haikou and Lhasa are predicted and analyzed. The results show that the prediction accuracy of the model based on Transformer is better than those of the traditional methods such as the model based on ARIMA and the model based on LSTM, and its mean absolute error (MAE) is 12.5% lower on average than that of the model based on LSTM, and its root mean square error (RMSE) is 13.98% lower on average than that of the model based on LSTM. In addition, its prediction error shows geographical differences (The prediction errors of the three stations in Beijing, Haikou, and Lhasa increase in sequence.) and seasonal changes (high in summer and low in winter), which is highly consistent with the physical mechanism of the ionosphere. The experiments verified the feasibility of the model based on Transformer in the prediction of ionospheric fbEs parameters.
[1] 唐琼.中低纬度电离层突发E层耦合特征和物理机制研究[D]. 武汉：武汉大学，2021.
[2] 孔庆颜，陈跃，柳文，等.中国典型区域Es特性研究[J].空间科学学报，2012，32（4）：506⁃512.
[3] Macleod M A, Keneshea T J, Narcisi R S. Numerical modelling of a metallic ion sporadic⁃E layer [J]. Radio Science, 1975, 10 (3): 371⁃388.
[4] 张雅彬，吴健，许正文，等.电离层Es离子分布数值建模[J].空间科学学报，2018，38（4）：452⁃459.
[5] Dungey J W. Cosmis electrodynamics [M]. London: Cambridge University Press, 2016.
[6] Tang Rongxin, Zeng Fantao, Chen Zhou, et al. The comparison of predicting storm ⁃ time ionospheric TEC by three methods: ARIMA, LSTM, and Seq2Seq [J]. Atmosphere, 2020, 11(4): 316. [7] 田晓鹏，罗亦泳，张紫怡.基于iInformer的电离层TEC短期预测[J].江西科学，2025，43（1）：52⁃58.
[8] Mathews J D. Sporadic E current views and recent progress [J]. Journal of Atmospheric and Solar⁃terrestrial Physics, 1998, 60 (4): 413⁃435.
[9] 王晓宾，马征征，张雅彬.青岛地区电离层Es特征统计分析[J].电波科学学报，2014，29（5）：969⁃972.
[10] Zhang Yabin, Wu Jian, Guo Lixin, et al. Influence of solar and geomagnetic activity on sporadic⁃E layer over low, mid and high latitude stations [J]. Advances in Space Research, 2015, 55(5): 1366⁃1371.
[11] 王胜.电离层Es的自动识别及其统计分析[D].武汉：武汉大学，2020.
[12] Pietrella M, Bianchi C. Occurrence of sporadic⁃E layer over the ionospheric station of Rome: Analysis of data for thirty⁃ two years [J]. Advances in Space Research, 2009, 44(1): 72⁃ 81.
[13] 李筱，马丽，岳甫璐.重庆地区电离层Es的遮蔽特性研究[J].装备环境工程，2023，20（2）：125⁃131.
[14] 冯蕴天，吴霞，许雄，等.基于深度学习的电离层参数预测研究[J].通信学报，2021，42（4）：202⁃206.
[15] Shi Yafei, Yang Cheng, Wang Jian, et al. A forecasting model of ionospheric foF2 using the LSTM network based on ICEEMDAN decomposition [J]. Transactions on Geoscience and Remote Sensing, 2023, 61(1): 1⁃16.
[16] Shi Yafei, Yang Cheng, Wang Jian, et al. A hybrid deep learning⁃based short⁃term forecast model for ionospheric foF2 in East Asia region [J]. Advances in Space Research, 2025, 75 (1): 988⁃1002.
[17] 刘海军，雷东兴，袁静，等.基于注意力机制LSTM的电离层TEC预测[J].地球物理学报，2024，67（2）：439⁃451.
[18] 王建敏，唐彦，吕楠，等.组合模型的电离层总电子短期预报研究[J].测绘科学，2022，47（4）：34⁃43.
[19] 罗欢，肖卉.含突发E层的电离层模型建立及其在测高中的应用[J].物理学报，2018，67（7）：270⁃281.
[20] 姜子欣，章浙涛，何秀凤，等.一种改进的单站TEC快速估计与短期预报方法[J].大地测量与地球动力学，2023，43（5）： 474⁃480.
Basic Information:
DOI：10.16652/j.issn.1004⁃373x.2026.09.016
Citation Information:
[1]Zhang Meng1, Huang Chaojun1, Feng Jian2 ,et al.Ionospheric fbEs short⁃term prediction based on Transformer[J].Modern Electronic Technique,2026(9):107-113.DOI:10.16652/j.issn.1004⁃373x.2026.09.016.
Fund Information:
陕西理工大学科研项目（SLGRCQD2009）