IonoGAN: An Enhanced Model for Forecasting Quiet and Disturbed Ionospheric Features From Predicted Ionograms

Abstract Ionograms are radar echo graphs that depict vertical ionospheric density profiles, structures, fluctuations, and irregularities, with the F region represented by F‐trace and Spread‐F features in the graphs. In this paper, IonoGAN, an enhanced neural network based on the Generative Adversari...

Full description

Saved in:
Bibliographic Details
Main Authors: Chu Qiu, Jinhui Cai, Zheng Wang, Pengdong Gao, Guojun Wang, Quan Qi, Bo Wang, Zhengwei Cheng, Jiankui Shi, Yajun Zhu, Xiao Wang, Kai Ding
Format: Article
Language:English
Published: Wiley 2025-06-01
Series:Space Weather
Subjects:
Online Access:https://doi.org/10.1029/2025SW004463
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849414908834217984
author Chu Qiu
Jinhui Cai
Zheng Wang
Pengdong Gao
Guojun Wang
Quan Qi
Bo Wang
Zhengwei Cheng
Jiankui Shi
Yajun Zhu
Xiao Wang
Kai Ding
author_facet Chu Qiu
Jinhui Cai
Zheng Wang
Pengdong Gao
Guojun Wang
Quan Qi
Bo Wang
Zhengwei Cheng
Jiankui Shi
Yajun Zhu
Xiao Wang
Kai Ding
author_sort Chu Qiu
collection DOAJ
description Abstract Ionograms are radar echo graphs that depict vertical ionospheric density profiles, structures, fluctuations, and irregularities, with the F region represented by F‐trace and Spread‐F features in the graphs. In this paper, IonoGAN, an enhanced neural network based on the Generative Adversarial Network architecture, is proposed for direct prediction of ionograms and the variation of these ionospheric conditions. This estimation is based on the trends of density profiles and the waves/structures presented in the ionogram sequence. The IonoGAN extends the spatiotemporal information‐preserving and perception‐augmented (STIP) ability by incorporating a Local‐Global discriminator to focus on the F region in ionograms. In addition, two scientific characteristics of ionospheric natural phenomena are extracted and used as constraints in the modeling: Spread‐F Classification Accuracy (SFCA) and Absolute Value of the Correlation Coefficient for the F trace (AVCC‐F). For training, ionograms from Hainan Fuke station (19.5°N, 109.1°E, magnetic 11°N) during 2002–2015 were processed into 36,435 sequences with Spread‐F phenomena and 147,147 sequences without. To strengthen their features, Spread‐F phenomena were further classified into types of frequency, range, mix, and strong range. After the parameter training, the IonoGAN achieved SFCA and AVCC‐F converging to their optimal values: on the 2016 test set, SFCA = 90.92%, AVCC‐F = 0.6917. This modification enables the network to effectively capture the distinct features of the ionospheric F trace and the Spread‐F phenomenon during both quiet and disturbed periods.
format Article
id doaj-art-01a94ded067d4d31b045e9a5166d423a
institution Kabale University
issn 1542-7390
language English
publishDate 2025-06-01
publisher Wiley
record_format Article
series Space Weather
spelling doaj-art-01a94ded067d4d31b045e9a5166d423a2025-08-20T03:33:41ZengWileySpace Weather1542-73902025-06-01236n/an/a10.1029/2025SW004463IonoGAN: An Enhanced Model for Forecasting Quiet and Disturbed Ionospheric Features From Predicted IonogramsChu Qiu0Jinhui Cai1Zheng Wang2Pengdong Gao3Guojun Wang4Quan Qi5Bo Wang6Zhengwei Cheng7Jiankui Shi8Yajun Zhu9Xiao Wang10Kai Ding11Key Laboratory of Media Audio & Video (Communication University of China) Ministry of Education Beijing ChinaState Key Laboratory of Media Convergence and Communication Communication University of China Beijing ChinaState Key Laboratory of Solar Activity and Space Weather National Space Science Center Chinese Academy of Sciences Beijing ChinaKey Laboratory of Media Audio & Video (Communication University of China) Ministry of Education Beijing ChinaState Key Laboratory of Solar Activity and Space Weather National Space Science Center Chinese Academy of Sciences Beijing ChinaKey Laboratory of Media Audio & Video (Communication University of China) Ministry of Education Beijing ChinaKey Laboratory of Media Audio & Video (Communication University of China) Ministry of Education Beijing ChinaState Key Laboratory of Solar Activity and Space Weather National Space Science Center Chinese Academy of Sciences Beijing ChinaState Key Laboratory of Solar Activity and Space Weather National Space Science Center Chinese Academy of Sciences Beijing ChinaState Key Laboratory of Solar Activity and Space Weather National Space Science Center Chinese Academy of Sciences Beijing ChinaState Key Laboratory of Solar Activity and Space Weather National Space Science Center Chinese Academy of Sciences Beijing ChinaState Key Laboratory of Solar Activity and Space Weather National Space Science Center Chinese Academy of Sciences Beijing ChinaAbstract Ionograms are radar echo graphs that depict vertical ionospheric density profiles, structures, fluctuations, and irregularities, with the F region represented by F‐trace and Spread‐F features in the graphs. In this paper, IonoGAN, an enhanced neural network based on the Generative Adversarial Network architecture, is proposed for direct prediction of ionograms and the variation of these ionospheric conditions. This estimation is based on the trends of density profiles and the waves/structures presented in the ionogram sequence. The IonoGAN extends the spatiotemporal information‐preserving and perception‐augmented (STIP) ability by incorporating a Local‐Global discriminator to focus on the F region in ionograms. In addition, two scientific characteristics of ionospheric natural phenomena are extracted and used as constraints in the modeling: Spread‐F Classification Accuracy (SFCA) and Absolute Value of the Correlation Coefficient for the F trace (AVCC‐F). For training, ionograms from Hainan Fuke station (19.5°N, 109.1°E, magnetic 11°N) during 2002–2015 were processed into 36,435 sequences with Spread‐F phenomena and 147,147 sequences without. To strengthen their features, Spread‐F phenomena were further classified into types of frequency, range, mix, and strong range. After the parameter training, the IonoGAN achieved SFCA and AVCC‐F converging to their optimal values: on the 2016 test set, SFCA = 90.92%, AVCC‐F = 0.6917. This modification enables the network to effectively capture the distinct features of the ionospheric F trace and the Spread‐F phenomenon during both quiet and disturbed periods.https://doi.org/10.1029/2025SW004463ionoganinongram predictionspread‐fneural networkionospheric disturbanceSTIP
spellingShingle Chu Qiu
Jinhui Cai
Zheng Wang
Pengdong Gao
Guojun Wang
Quan Qi
Bo Wang
Zhengwei Cheng
Jiankui Shi
Yajun Zhu
Xiao Wang
Kai Ding
IonoGAN: An Enhanced Model for Forecasting Quiet and Disturbed Ionospheric Features From Predicted Ionograms
Space Weather
ionogan
inongram prediction
spread‐f
neural network
ionospheric disturbance
STIP
title IonoGAN: An Enhanced Model for Forecasting Quiet and Disturbed Ionospheric Features From Predicted Ionograms
title_full IonoGAN: An Enhanced Model for Forecasting Quiet and Disturbed Ionospheric Features From Predicted Ionograms
title_fullStr IonoGAN: An Enhanced Model for Forecasting Quiet and Disturbed Ionospheric Features From Predicted Ionograms
title_full_unstemmed IonoGAN: An Enhanced Model for Forecasting Quiet and Disturbed Ionospheric Features From Predicted Ionograms
title_short IonoGAN: An Enhanced Model for Forecasting Quiet and Disturbed Ionospheric Features From Predicted Ionograms
title_sort ionogan an enhanced model for forecasting quiet and disturbed ionospheric features from predicted ionograms
topic ionogan
inongram prediction
spread‐f
neural network
ionospheric disturbance
STIP
url https://doi.org/10.1029/2025SW004463
work_keys_str_mv AT chuqiu ionogananenhancedmodelforforecastingquietanddisturbedionosphericfeaturesfrompredictedionograms
AT jinhuicai ionogananenhancedmodelforforecastingquietanddisturbedionosphericfeaturesfrompredictedionograms
AT zhengwang ionogananenhancedmodelforforecastingquietanddisturbedionosphericfeaturesfrompredictedionograms
AT pengdonggao ionogananenhancedmodelforforecastingquietanddisturbedionosphericfeaturesfrompredictedionograms
AT guojunwang ionogananenhancedmodelforforecastingquietanddisturbedionosphericfeaturesfrompredictedionograms
AT quanqi ionogananenhancedmodelforforecastingquietanddisturbedionosphericfeaturesfrompredictedionograms
AT bowang ionogananenhancedmodelforforecastingquietanddisturbedionosphericfeaturesfrompredictedionograms
AT zhengweicheng ionogananenhancedmodelforforecastingquietanddisturbedionosphericfeaturesfrompredictedionograms
AT jiankuishi ionogananenhancedmodelforforecastingquietanddisturbedionosphericfeaturesfrompredictedionograms
AT yajunzhu ionogananenhancedmodelforforecastingquietanddisturbedionosphericfeaturesfrompredictedionograms
AT xiaowang ionogananenhancedmodelforforecastingquietanddisturbedionosphericfeaturesfrompredictedionograms
AT kaiding ionogananenhancedmodelforforecastingquietanddisturbedionosphericfeaturesfrompredictedionograms