A Hybrid Deep Learning‐Based Forecasting Model for the Peak Height of Ionospheric F2 Layer

IF 3.8 2区 地球科学 Q2 ASTRONOMY & ASTROPHYSICS
Ya‐fei Shi, Cheng Yang, Jian Wang, Yu Zheng, Fan‐yi Meng, Leonid F. Chernogor
{"title":"A Hybrid Deep Learning‐Based Forecasting Model for the Peak Height of Ionospheric F2 Layer","authors":"Ya‐fei Shi, Cheng Yang, Jian Wang, Yu Zheng, Fan‐yi Meng, Leonid F. Chernogor","doi":"10.1029/2023sw003581","DOIUrl":null,"url":null,"abstract":"Abstract To achieve accurate forecasting of the peak height of the ionospheric F2 layer (hmF2), we propose a hybrid deep learning model of improved seagull optimization algorithm (ISOA) optimized long short‐term memory (LSTM) model based on a complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) theory. The hybrid model decomposes the hmF2 time data into multiple subsequences through CEEMDAN and reconstructs the subsequences by sample entropy and correlation coefficient into high and low‐frequency sequences, which effectively shortens the calculation time of the model. Then, we determine the optimal hyperparameters of the LSTM models through ISOA, achieving high‐precision forecasting of the hmF2. In single‐step forecasting, the forecasting values of the hybrid model in diurnal and seasonal changes are highly consistent with the observation, which can better capture the severe changes in the hmF2. The model's RMSE, MAE, MAPE, and CC evaluation metrics are 15.86, 11.03 km, 4.76%, and 0.93 in the test set. Compared to IRI, GRU, and LSTM models, taking RMSE as an example, the forecasting accuracy of the models increased by 65.24%, 29.89%, and 29.60%, respectively. In multi‐step forecasting, the proposed model is better at forecasting the changing trend of hmF2, and the forecasting accuracies are significantly better than the IRI model. The data from multiple stations also verified the applicability of the proposed model for hmF2 forecasting. The above results indicate that the hybrid model has high accuracy in hmF2 short‐term forecasting and good applicability in multiple multi‐step forecasting, which can further improve the accurate forecasting of space weather.","PeriodicalId":49487,"journal":{"name":"Space Weather-The International Journal of Research and Applications","volume":null,"pages":null},"PeriodicalIF":3.8000,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Space Weather-The International Journal of Research and Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1029/2023sw003581","RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ASTRONOMY & ASTROPHYSICS","Score":null,"Total":0}
引用次数: 1

Abstract

Abstract To achieve accurate forecasting of the peak height of the ionospheric F2 layer (hmF2), we propose a hybrid deep learning model of improved seagull optimization algorithm (ISOA) optimized long short‐term memory (LSTM) model based on a complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) theory. The hybrid model decomposes the hmF2 time data into multiple subsequences through CEEMDAN and reconstructs the subsequences by sample entropy and correlation coefficient into high and low‐frequency sequences, which effectively shortens the calculation time of the model. Then, we determine the optimal hyperparameters of the LSTM models through ISOA, achieving high‐precision forecasting of the hmF2. In single‐step forecasting, the forecasting values of the hybrid model in diurnal and seasonal changes are highly consistent with the observation, which can better capture the severe changes in the hmF2. The model's RMSE, MAE, MAPE, and CC evaluation metrics are 15.86, 11.03 km, 4.76%, and 0.93 in the test set. Compared to IRI, GRU, and LSTM models, taking RMSE as an example, the forecasting accuracy of the models increased by 65.24%, 29.89%, and 29.60%, respectively. In multi‐step forecasting, the proposed model is better at forecasting the changing trend of hmF2, and the forecasting accuracies are significantly better than the IRI model. The data from multiple stations also verified the applicability of the proposed model for hmF2 forecasting. The above results indicate that the hybrid model has high accuracy in hmF2 short‐term forecasting and good applicability in multiple multi‐step forecasting, which can further improve the accurate forecasting of space weather.
基于深度学习的电离层F2层峰值高度混合预测模型
摘要为了实现对电离层F2层(hmF2)峰高的准确预测,提出了一种基于自适应噪声(CEEMDAN)理论的全综经验模态分解的改进海鸥优化算法(ISOA)优化长短期记忆(LSTM)模型的混合深度学习模型。该混合模型通过CEEMDAN将hmF2时间数据分解为多个子序列,并通过样本熵和相关系数将子序列重构为高频和低频序列,有效缩短了模型的计算时间。然后,我们通过ISOA确定LSTM模型的最优超参数,实现对hmF2的高精度预测。在单步预报中,混合模型对日变化和季节变化的预测值与观测值高度一致,能较好地捕捉hmF2的剧烈变化。模型的RMSE、MAE、MAPE和CC评价指标在测试集中分别为15.86、11.03 km、4.76%和0.93。与IRI、GRU和LSTM模型相比,以RMSE为例,模型的预测准确率分别提高了65.24%、29.89%和29.60%。在多步预测中,该模型能较好地预测hmF2的变化趋势,预测精度明显优于IRI模型。多个台站的数据也验证了该模型对hmF2预报的适用性。上述结果表明,该混合模型在hmF2短期预报中具有较高的精度,在多个多步预报中具有较好的适用性,可进一步提高空间天气预报的准确性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
5.90
自引率
29.70%
发文量
166
审稿时长
>12 weeks
期刊介绍: Space Weather: The International Journal of Research and Applications (SWE) is devoted to understanding and forecasting space weather. The scope of understanding and forecasting includes: origins, propagation and interactions of solar-produced processes within geospace; interactions in Earth’s space-atmosphere interface region produced by disturbances from above and below; influences of cosmic rays on humans, hardware, and signals; and comparisons of these types of interactions and influences with the atmospheres of neighboring planets and Earth’s moon. Manuscripts should emphasize impacts on technical systems including telecommunications, transportation, electric power, satellite navigation, avionics/spacecraft design and operations, human spaceflight, and other systems. Manuscripts that describe models or space environment climatology should clearly state how the results can be applied.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信