TEC Map Completion Through a Deep Learning Model: SNP‐GAN
Abstract The limited availability of ground receiver stations causes an approximate 52% of data gaps in Massachusetts Institute of Technology (MIT)‐ total electron content (TEC) global maps. The completed TEC maps are highly desirable for both scientific research and space weather applications. Comp...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-11-01
|
| Series: | Space Weather |
| Online Access: | https://doi.org/10.1029/2021SW002810 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536473169395712 |
|---|---|
| author | Yang Pan Mingwu Jin Shunrong Zhang Yue Deng |
| author_facet | Yang Pan Mingwu Jin Shunrong Zhang Yue Deng |
| author_sort | Yang Pan |
| collection | DOAJ |
| description | Abstract The limited availability of ground receiver stations causes an approximate 52% of data gaps in Massachusetts Institute of Technology (MIT)‐ total electron content (TEC) global maps. The completed TEC maps are highly desirable for both scientific research and space weather applications. Compared to the conventional image inpainting methods, the deep learning methods using generative adversarial networks (GANs) offer an effective image inpainting tool. We adapt the Spectrally Normalized Patch GAN (SNP‐GAN) for the TEC map completion using a traditional complete TEC data source, the International Global Navigation Satellite System TEC (IGS‐TEC) maps, as the training data. For 10‐fold cross‐validation of 20‐year IGS‐TEC data, SNP‐GAN reduces the root mean squared error (RMSE) by more than 30% compared to our previous model, the deep convolutional GAN with Poisson blending (DCGAN‐PB). Two case studies using MIT‐TEC data for 2013 and 2016 storms also demonstrate that SNP‐GAN outperforms DCGAN‐PB in terms of recovering equatorial and low latitude TEC structures. Meanwhile, the end‐to‐end styled generator of SNP‐GAN saves time in the map completion step by avoiding iterative mapping used in DCGAN‐PB. Both deep learning methods not only preserve the large‐scale TEC structures well, but also reveal mesoscale (100–1,000 km) TEC structures that are missing in IGS‐TEC. This work represents an important progress for efficient and automatic TEC map completion with high accuracy. |
| format | Article |
| id | doaj-art-3b33639037b6492a9bc5e53254db7a36 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2021-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-3b33639037b6492a9bc5e53254db7a362025-01-14T16:27:04ZengWileySpace Weather1542-73902021-11-011911n/an/a10.1029/2021SW002810TEC Map Completion Through a Deep Learning Model: SNP‐GANYang Pan0Mingwu Jin1Shunrong Zhang2Yue Deng3University of Texas at Arlington Arlington TX USAUniversity of Texas at Arlington Arlington TX USAHaystack Observatory Massachusetts Institute of Technology Westford MA USAUniversity of Texas at Arlington Arlington TX USAAbstract The limited availability of ground receiver stations causes an approximate 52% of data gaps in Massachusetts Institute of Technology (MIT)‐ total electron content (TEC) global maps. The completed TEC maps are highly desirable for both scientific research and space weather applications. Compared to the conventional image inpainting methods, the deep learning methods using generative adversarial networks (GANs) offer an effective image inpainting tool. We adapt the Spectrally Normalized Patch GAN (SNP‐GAN) for the TEC map completion using a traditional complete TEC data source, the International Global Navigation Satellite System TEC (IGS‐TEC) maps, as the training data. For 10‐fold cross‐validation of 20‐year IGS‐TEC data, SNP‐GAN reduces the root mean squared error (RMSE) by more than 30% compared to our previous model, the deep convolutional GAN with Poisson blending (DCGAN‐PB). Two case studies using MIT‐TEC data for 2013 and 2016 storms also demonstrate that SNP‐GAN outperforms DCGAN‐PB in terms of recovering equatorial and low latitude TEC structures. Meanwhile, the end‐to‐end styled generator of SNP‐GAN saves time in the map completion step by avoiding iterative mapping used in DCGAN‐PB. Both deep learning methods not only preserve the large‐scale TEC structures well, but also reveal mesoscale (100–1,000 km) TEC structures that are missing in IGS‐TEC. This work represents an important progress for efficient and automatic TEC map completion with high accuracy.https://doi.org/10.1029/2021SW002810 |
| spellingShingle | Yang Pan Mingwu Jin Shunrong Zhang Yue Deng TEC Map Completion Through a Deep Learning Model: SNP‐GAN Space Weather |
| title | TEC Map Completion Through a Deep Learning Model: SNP‐GAN |
| title_full | TEC Map Completion Through a Deep Learning Model: SNP‐GAN |
| title_fullStr | TEC Map Completion Through a Deep Learning Model: SNP‐GAN |
| title_full_unstemmed | TEC Map Completion Through a Deep Learning Model: SNP‐GAN |
| title_short | TEC Map Completion Through a Deep Learning Model: SNP‐GAN |
| title_sort | tec map completion through a deep learning model snp gan |
| url | https://doi.org/10.1029/2021SW002810 |
| work_keys_str_mv | AT yangpan tecmapcompletionthroughadeeplearningmodelsnpgan AT mingwujin tecmapcompletionthroughadeeplearningmodelsnpgan AT shunrongzhang tecmapcompletionthroughadeeplearningmodelsnpgan AT yuedeng tecmapcompletionthroughadeeplearningmodelsnpgan |