Global Ionospheric TEC Map Prediction Based on Multichannel ED-PredRNN

High-precision total electron content (TEC) prediction can improve the accuracy of the Global Navigation Satellite System (GNSS)-based applications. The existing deep learning models for TEC prediction mainly include long short-term memory (LSTM), convolutional long short-term memory (ConvLSTM), and...

Full description

Saved in:
Bibliographic Details
Main Authors: Haijun Liu, Yan Ma, Huijun Le, Liangchao Li, Rui Zhou, Jian Xiao, Weifeng Shan, Zhongxiu Wu, Yalan Li
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Atmosphere
Subjects:
Online Access:https://www.mdpi.com/2073-4433/16/4/422
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850144245342535680
author Haijun Liu
Yan Ma
Huijun Le
Liangchao Li
Rui Zhou
Jian Xiao
Weifeng Shan
Zhongxiu Wu
Yalan Li
author_facet Haijun Liu
Yan Ma
Huijun Le
Liangchao Li
Rui Zhou
Jian Xiao
Weifeng Shan
Zhongxiu Wu
Yalan Li
author_sort Haijun Liu
collection DOAJ
description High-precision total electron content (TEC) prediction can improve the accuracy of the Global Navigation Satellite System (GNSS)-based applications. The existing deep learning models for TEC prediction mainly include long short-term memory (LSTM), convolutional long short-term memory (ConvLSTM), and their variants, which contain only one temporal memory. These models may result in fuzzy prediction results due to neglecting spatial memory, as spatial memory is crucial for capturing the correlations of TEC within the TEC neighborhood. In this paper, we draw inspiration from the predictive recurrent neural network (PredRNN), which has dual memory states to construct a TEC prediction model named Multichannel ED-PredRNN. The highlights of our work include the following: (1) for the first time, a dual memory mechanism was utilized in TEC prediction, which can more fully capture the temporal and spatial features; (2) we modified the n vs. n structure of original PredRNN to an encoder–decoder structure, so as to handle the problem of unequal input and output lengths in TEC prediction; and (3) we expanded the feature channels by extending the Kp, Dst, and F10.7 to the same spatiotemporal resolution as global TEC maps, overlaying them together to form multichannel features, so as to fully utilize the influence of solar and geomagnetic activities on TEC. The proposed Multichannel ED-PredRNN was compared with COPG, ConvLSTM, and convolutional gated recurrent unit (ConvGRU) from multiple perspectives on a data set of 6 years, including comparisons at different solar activities, time periods, latitude regions, single stations, and geomagnetic storm periods. The results show that in almost all cases, the proposed Multichannel ED-PredRNN outperforms the three comparative models, indicating that it can more fully utilize temporal and spatial features to improve the accuracy of TEC prediction.
format Article
id doaj-art-78097842263142b68540266dcf7ffede
institution OA Journals
issn 2073-4433
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Atmosphere
spelling doaj-art-78097842263142b68540266dcf7ffede2025-08-20T02:28:27ZengMDPI AGAtmosphere2073-44332025-04-0116442210.3390/atmos16040422Global Ionospheric TEC Map Prediction Based on Multichannel ED-PredRNNHaijun Liu0Yan Ma1Huijun Le2Liangchao Li3Rui Zhou4Jian Xiao5Weifeng Shan6Zhongxiu Wu7Yalan Li8Institute of Intelligent Emergency Information Processing, Institute of Disaster Prevention, Langfang 065201, ChinaInstitute of Intelligent Emergency Information Processing, Institute of Disaster Prevention, Langfang 065201, ChinaKey Laboratory of Earth and Planetary Physics, Institute of Geology and Geophysics, Chinese Academy of Sciences, Beijing 100029, ChinaSchool of Information Engineering, China University of Geosciences, Beijing 100029, ChinaInstitute of Intelligent Emergency Information Processing, Institute of Disaster Prevention, Langfang 065201, ChinaInstitute of Intelligent Emergency Information Processing, Institute of Disaster Prevention, Langfang 065201, ChinaInstitute of Intelligent Emergency Information Processing, Institute of Disaster Prevention, Langfang 065201, ChinaCollege of General Education, Hainan Vocational University, Haikou 570216, ChinaMicroelectronics and Optoelectronics Technology Key Laboratory of Hunan Higher Education, School of Physics and Electronic Electrical Engineering, Xiangnan University, Chenzhou 423000, ChinaHigh-precision total electron content (TEC) prediction can improve the accuracy of the Global Navigation Satellite System (GNSS)-based applications. The existing deep learning models for TEC prediction mainly include long short-term memory (LSTM), convolutional long short-term memory (ConvLSTM), and their variants, which contain only one temporal memory. These models may result in fuzzy prediction results due to neglecting spatial memory, as spatial memory is crucial for capturing the correlations of TEC within the TEC neighborhood. In this paper, we draw inspiration from the predictive recurrent neural network (PredRNN), which has dual memory states to construct a TEC prediction model named Multichannel ED-PredRNN. The highlights of our work include the following: (1) for the first time, a dual memory mechanism was utilized in TEC prediction, which can more fully capture the temporal and spatial features; (2) we modified the n vs. n structure of original PredRNN to an encoder–decoder structure, so as to handle the problem of unequal input and output lengths in TEC prediction; and (3) we expanded the feature channels by extending the Kp, Dst, and F10.7 to the same spatiotemporal resolution as global TEC maps, overlaying them together to form multichannel features, so as to fully utilize the influence of solar and geomagnetic activities on TEC. The proposed Multichannel ED-PredRNN was compared with COPG, ConvLSTM, and convolutional gated recurrent unit (ConvGRU) from multiple perspectives on a data set of 6 years, including comparisons at different solar activities, time periods, latitude regions, single stations, and geomagnetic storm periods. The results show that in almost all cases, the proposed Multichannel ED-PredRNN outperforms the three comparative models, indicating that it can more fully utilize temporal and spatial features to improve the accuracy of TEC prediction.https://www.mdpi.com/2073-4433/16/4/422total electron content (TEC)multichannel ED-PredRNNspatiotemporal predictionsolar activitymagnetic storms
spellingShingle Haijun Liu
Yan Ma
Huijun Le
Liangchao Li
Rui Zhou
Jian Xiao
Weifeng Shan
Zhongxiu Wu
Yalan Li
Global Ionospheric TEC Map Prediction Based on Multichannel ED-PredRNN
Atmosphere
total electron content (TEC)
multichannel ED-PredRNN
spatiotemporal prediction
solar activity
magnetic storms
title Global Ionospheric TEC Map Prediction Based on Multichannel ED-PredRNN
title_full Global Ionospheric TEC Map Prediction Based on Multichannel ED-PredRNN
title_fullStr Global Ionospheric TEC Map Prediction Based on Multichannel ED-PredRNN
title_full_unstemmed Global Ionospheric TEC Map Prediction Based on Multichannel ED-PredRNN
title_short Global Ionospheric TEC Map Prediction Based on Multichannel ED-PredRNN
title_sort global ionospheric tec map prediction based on multichannel ed predrnn
topic total electron content (TEC)
multichannel ED-PredRNN
spatiotemporal prediction
solar activity
magnetic storms
url https://www.mdpi.com/2073-4433/16/4/422
work_keys_str_mv AT haijunliu globalionospherictecmappredictionbasedonmultichanneledpredrnn
AT yanma globalionospherictecmappredictionbasedonmultichanneledpredrnn
AT huijunle globalionospherictecmappredictionbasedonmultichanneledpredrnn
AT liangchaoli globalionospherictecmappredictionbasedonmultichanneledpredrnn
AT ruizhou globalionospherictecmappredictionbasedonmultichanneledpredrnn
AT jianxiao globalionospherictecmappredictionbasedonmultichanneledpredrnn
AT weifengshan globalionospherictecmappredictionbasedonmultichanneledpredrnn
AT zhongxiuwu globalionospherictecmappredictionbasedonmultichanneledpredrnn
AT yalanli globalionospherictecmappredictionbasedonmultichanneledpredrnn