当前位置: X-MOL 学术Astrophys. Space Sci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Ionospheric TEC prediction using Long Short-Term Memory deep learning network
Astrophysics and Space Science ( IF 1.8 ) Pub Date : 2021-01-01 , DOI: 10.1007/s10509-020-03907-1
Zhichao Wen , Shuhui Li , Lihua Li , Bowen Wu , Jianqiang Fu

In this paper, the prediction model for ionospheric total electron content (TEC) based on Long Short-Term Memory (LSTM) deep learning network and its performance are discussed. The input parameters of the model are previous values of daily TEC, solar radio flux at 10.7 cm parameter of 81 day moving average ( F 107 _ 81 ‾ $\overline{F107\_81}$ ), sunspot number (SSN), geomagnetic Kp index, and disturbance storm time (Dst) index, and the outputs are TEC values for the target day. TEC data from January 1, 2001 to December 31, 2016 were used in this study. The dataset almost covers most of the years of the last two solar cycles (23, 24), and it is separated as 81.3% for training, 6.2% for validation, and 12.5% for testing. At BJFS IGS station (39.61° N, 115.89° E), LSTM yielded good TEC estimates with an RMSE of 4.07 TECU in 2001, it was 33% and 48% lower than the RMSE observed in TEC prediction using BP and IRI-2016 models, respectively. In the year of low solar activity (2016), the RMSE predicted by LSTM was 1.78 TECU, it provided 30% and 54% lower RMSE for TEC prediction than for BP and IRI-2016 models. Under the condition of magnetic storm, the LSTM TEC predictions are more consistent with the corresponding IGS Global Ionospheric Maps (GIMs) TEC than TEC predictions by BP and IRI-2016 models. LSTM can better grasp the influence of different external conditions on TEC. Seventeen grid points along 120° E meridian in latitude range from 80° S to 80° N were selected to further study the performance of LSTM model in different latitude. Results show that the prediction accuracy of LSTM is better than that of BP at different latitudes, especially at low latitudes. The performances of the two models are highly correlated with latitude and solar activity, and are both better than that of IRI-2016.

中文翻译:

使用长短期记忆深度学习网络的电离层 TEC 预测

本文讨论了基于长短期记忆(LSTM)深度学习网络的电离层总电子含量(TEC)预测模型及其性能。模型的输入参数是日 TEC 的先前值、81 天移动平均线的 10.7 cm 处的太阳射电通量参数 ( F 107 _ 81 ‾ $\overline{F107\_81}$ )、太阳黑子数 (SSN)、地磁 Kp指数和扰动风暴时间 (Dst) 指数,输出是目标日的 TEC 值。本研究使用了2001年1月1日至2016年12月31日的TEC数据。该数据集几乎涵盖了最近两个太阳周期(23、24)的大部分年份,并将其分为训练的 81.3%、验证的 6.2% 和测试的 12.5%。在 BJFS IGS 站(北纬 39.61°,东经 115.89°),LSTM 产生了良好的 TEC 估计,2001 年的 RMSE 为 4.07 TECU,它分别比使用 BP 和 IRI-2016 模型在 TEC 预测中观察到的 RMSE 低 33% 和 48%。在太阳活动较低的年份(2016 年),LSTM 预测的 RMSE 为 1.78 TECU,它提供的 TEC 预测的 RMSE 比 BP 和 IRI-2016 模型低 30% 和 54%。在磁暴条件下,LSTM TEC 预测与相应的 IGS 全球电离层图 (GIM) TEC 比 BP 和 IRI-2016 模型的 TEC 预测更一致。LSTM 可以更好地掌握不同外部条件对 TEC 的影响。选择了纬度范围从 80° S 到 80° N 的 120° E 子午线的 17 个网格点,以进一步研究 LSTM 模型在不同纬度下的性能。结果表明,LSTM的预测精度在不同纬度上均优于BP,尤其是在低纬度地区。
更新日期:2021-01-01
down
wechat
bug