2021
DOI: 10.1029/2020ja028418
|View full text |Cite
|
Sign up to set email alerts
|

The Application of a Deep Convolutional Generative Adversarial Network on Completing Global TEC Maps

Abstract: Total electron content (TEC) representing the integrated electron density from satellites to the receivers is one of the important parameters which can monitor the condition of space weather and provide valuable information for navigation improvement (Coster et al., 2008). With the rapid development of the technologies of ionospheric observation, such as the GPS-based measurement (Jakowski et al., 2002) and groundbased measurement, a mass of TEC data are available. Benefit from the continuous observation of GP… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
8
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5

Relationship

1
4

Authors

Journals

citations
Cited by 9 publications
(8 citation statements)
references
References 26 publications
0
8
0
Order By: Relevance
“…And J. Chen et al. (2021) proposed a new method of Global and Local Generative Adversarial Network (GLGAN) and applied it to the completion of global TEC mapping. GLGAN uses two discriminators: global discriminator and local discriminator.…”
Section: Introductionmentioning
confidence: 99%
“…And J. Chen et al. (2021) proposed a new method of Global and Local Generative Adversarial Network (GLGAN) and applied it to the completion of global TEC mapping. GLGAN uses two discriminators: global discriminator and local discriminator.…”
Section: Introductionmentioning
confidence: 99%
“…A distinguishing ionospheric structure in global TEC maps is the Equatorial Ionization Anomaly (EIA), which consists of an ionization trough along the magnetic equator and ionization crests around ±10°-15° geomagnetic latitudes (Hanson & Moffett, 1966). Previous research on completing global TEC maps using deep learning techniques has focused on reconstructing the EIA because other structures appear to be minor features compared to the EIA (Chen et al, 2019(Chen et al, , 2021Ji et al, 2020;Pan et al, 2020). Although global TEC maps are useful for investigating global ionospheric phenomena, users of TEC maps for practical or operational purposes are more interested in having quick access to reliable local TEC maps.…”
mentioning
confidence: 99%
“…Deep learning techniques based on generative adversarial network (GAN) (Goodfellow et al, 2014) have recently been used to complete global TEC maps (Chen et al, 2019(Chen et al, , 2021Ji et al, 2020;Pan et al, 2020). A GAN consists of two components: a generator and a discriminator.…”
mentioning
confidence: 99%
“…Deep learning brings a breakthrough to solving the problem that results from the lack of data. Among the various deep learning methods, the generative adversarial network (GAN) exhibits great potential in recovering missing data (Chen et al, 2021;Chen et al, 2019;Pan et al, 2020Pan et al, , 2021. Generative adversarial network (GAN) is trained for extracting the features of pictures through the competition between the generator and discriminator.…”
mentioning
confidence: 99%
“…Their model reduced the root mean square error (RMSE) by more than 30% compared to DCGAN-PB. Chen et al (2021) proposed Global and Local GAN (GLGAN), which has two discriminators to complete the global TEC maps. The design enhanced the ability to judge the quality of the output images and shortened the time of training.…”
mentioning
confidence: 99%