Global TEC Map Fusion Through a Hybrid Deep Learning Model: RFGAN
Abstract Timely, reliable and comprehensive global observation information is essential for space weather research. However, limited observation technology hinders the consecutive global coverage of observation data. For the integrity and continuity of the global observation data, deep learning can...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-01-01
|
| Series: | Space Weather |
| Online Access: | https://doi.org/10.1029/2022SW003341 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536318859902976 |
|---|---|
| author | Zhou Chen Kecheng Zhou Haimeng Li Jing‐song Wang Zhihai Ouyang Xiaohua Deng |
| author_facet | Zhou Chen Kecheng Zhou Haimeng Li Jing‐song Wang Zhihai Ouyang Xiaohua Deng |
| author_sort | Zhou Chen |
| collection | DOAJ |
| description | Abstract Timely, reliable and comprehensive global observation information is essential for space weather research. However, limited observation technology hinders the consecutive global coverage of observation data. For the integrity and continuity of the global observation data, deep learning can obtain a global Ionospheric total electron content (TEC) map by fusing multi‐source TEC maps. Different from the previous methods, in the study, a deep learning hybrid model (RFGAN) based on Dual‐Discriminator Conditional Generative Adversarial Network (DDcGAN) and Free‐Form Image Inpainting with Gated Convolution (Deepfill v2) is proposed to fuse the Massachusetts Institute of Technology (MIT)—TEC, International Global Navigation Satellite System TEC (IGS‐TEC) and altimetry satellite TEC. Throughout the RFGAN structure, we use an autoencoder model with gated convolution to inpaint the missing parts of MIT‐TEC and altimetry satellite TEC. Meanwhile, DDcGAN fuses the inpainted MIT‐TEC (MIT'‐TEC) and IGS‐TEC to get a global TEC map with high accuracy. To a certain extent, we inpainted the ocean area of MIT‐TEC through RFGAN. At the same time, RFGAN keeps the consistency of RFGAN‐TEC and MIT‐TEC in the continent area. Our proposed deep learning hybrid model can be easily extended and widely applied to other fields of space science, especially in addressing observational data loss and multi‐source data fusion. |
| format | Article |
| id | doaj-art-2eb7fccff9ea4b6a9ef9acbcf2174a30 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-2eb7fccff9ea4b6a9ef9acbcf2174a302025-01-14T16:35:23ZengWileySpace Weather1542-73902023-01-01211n/an/a10.1029/2022SW003341Global TEC Map Fusion Through a Hybrid Deep Learning Model: RFGANZhou Chen0Kecheng Zhou1Haimeng Li2Jing‐song Wang3Zhihai Ouyang4Xiaohua Deng5School of Information Engineering Nanchang University Nanchang ChinaSchool of Information Engineering Nanchang University Nanchang ChinaSchool of Information Engineering Nanchang University Nanchang ChinaKey Laboratory of Space Weather National Center for Space Weather China Meteorological Administration Beijing ChinaSchool of Information Engineering Nanchang University Nanchang ChinaSchool of Information Engineering Nanchang University Nanchang ChinaAbstract Timely, reliable and comprehensive global observation information is essential for space weather research. However, limited observation technology hinders the consecutive global coverage of observation data. For the integrity and continuity of the global observation data, deep learning can obtain a global Ionospheric total electron content (TEC) map by fusing multi‐source TEC maps. Different from the previous methods, in the study, a deep learning hybrid model (RFGAN) based on Dual‐Discriminator Conditional Generative Adversarial Network (DDcGAN) and Free‐Form Image Inpainting with Gated Convolution (Deepfill v2) is proposed to fuse the Massachusetts Institute of Technology (MIT)—TEC, International Global Navigation Satellite System TEC (IGS‐TEC) and altimetry satellite TEC. Throughout the RFGAN structure, we use an autoencoder model with gated convolution to inpaint the missing parts of MIT‐TEC and altimetry satellite TEC. Meanwhile, DDcGAN fuses the inpainted MIT‐TEC (MIT'‐TEC) and IGS‐TEC to get a global TEC map with high accuracy. To a certain extent, we inpainted the ocean area of MIT‐TEC through RFGAN. At the same time, RFGAN keeps the consistency of RFGAN‐TEC and MIT‐TEC in the continent area. Our proposed deep learning hybrid model can be easily extended and widely applied to other fields of space science, especially in addressing observational data loss and multi‐source data fusion.https://doi.org/10.1029/2022SW003341 |
| spellingShingle | Zhou Chen Kecheng Zhou Haimeng Li Jing‐song Wang Zhihai Ouyang Xiaohua Deng Global TEC Map Fusion Through a Hybrid Deep Learning Model: RFGAN Space Weather |
| title | Global TEC Map Fusion Through a Hybrid Deep Learning Model: RFGAN |
| title_full | Global TEC Map Fusion Through a Hybrid Deep Learning Model: RFGAN |
| title_fullStr | Global TEC Map Fusion Through a Hybrid Deep Learning Model: RFGAN |
| title_full_unstemmed | Global TEC Map Fusion Through a Hybrid Deep Learning Model: RFGAN |
| title_short | Global TEC Map Fusion Through a Hybrid Deep Learning Model: RFGAN |
| title_sort | global tec map fusion through a hybrid deep learning model rfgan |
| url | https://doi.org/10.1029/2022SW003341 |
| work_keys_str_mv | AT zhouchen globaltecmapfusionthroughahybriddeeplearningmodelrfgan AT kechengzhou globaltecmapfusionthroughahybriddeeplearningmodelrfgan AT haimengli globaltecmapfusionthroughahybriddeeplearningmodelrfgan AT jingsongwang globaltecmapfusionthroughahybriddeeplearningmodelrfgan AT zhihaiouyang globaltecmapfusionthroughahybriddeeplearningmodelrfgan AT xiaohuadeng globaltecmapfusionthroughahybriddeeplearningmodelrfgan |