We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
TEC Map Completion Through a Deep Learning Model: SNP‐GAN.
- Authors
Pan, Yang; Jin, Mingwu; Zhang, Shunrong; Deng, Yue
- 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. Plain Language Summary: The Massachusetts Institute of Technology (MIT) global total electron content (TEC) map has missing data primarily over the oceans due to the limited coverage of TEC ground receiver stations. We propose a novel deep learning method to learn TEC data distribution from the International Global Navigation Satellite System Service (IGS)‐TEC database to fill the missing data in MIT‐TEC maps. IGS‐TEC is a data assimilation product without data gaps, however, it smooths out mesoscale (100–1,000 km) structures. Both quantitative and qualitative results show the superior performance of the proposed method compared to the previous deep learning method. Our model can not only preserve the large‐scale TEC structures, but also reveal mesoscale TEC structures that are lack in IGS‐TEC. Key Points: A novel spectrally normalized patch generative adversarial network (SNP‐GAN) is adapted to achieve the end‐to‐end automatic completion of total electron content mapsThe newly proposed deep learning model outperforms our previous model in terms of reconstruction accuracy, recovery of peak structures and computational efficiencyThe deep learning methods can reconstruct not only large‐scale structures included in the traditional complete total electron content maps, but also medium‐scale structures that are lack in the traditional complete maps
- Subjects
TOTAL electron content (Atmosphere); STANDARD deviations; IONOSPHERE; SPACE environment; DEEP learning
- Publication
Space Weather: The International Journal of Research & Applications, 2021, Vol 19, Issue 11, p1
- ISSN
1539-4956
- Publication type
Article
- DOI
10.1029/2021SW002810