Because of the limited coverage of global navigation satellite system (GNSS) receivers, total electron content (TEC) maps are not complete. The processing to obtain complete TEC maps is time consuming and needs the collaboration of five international GNSS service (IGS) centers to consolidate final completed IGS TEC maps. The advance of deep learning offers powerful tools to perform certain tasks in data science, such as image completion (or inpainting). Among them, deep convolutional generative adversarial network (DCGAN) is capable of learning the properties of the objects and recovering missing data effectively. With years of IGS TEC maps for training, the combination of DCGAN and Poisson blending (DCGAN-PB) is able to effectively learn the completion process of IGS TEC maps. Both random and more realistic masks are used to test the performance of DCGAN-PB. The results with random masks (15-40% missing data) show that DCGAN-PB can achieve better TEC map completion than DCGAN alone, and more training data can significantly improve its generalization. For the cross-validation experiment using the realistic mask from Massachusetts Institute of Technology (MIT)-TEC data (~52% missing data), DCGAN-PB achieves the average root mean squared error about three absolute TEC units (TECu) for high solar activity years and less than two TECu for low solar activity years, which is about 50% reduction of means and more than 50% reduction on standard deviations compared to two conventional single-image inpainting methods. The DCGAN-PB model can lead to an efficient automatic completion tool for TEC maps by minimizing the manual work. Plain Language Summary The limited number of global positioning system (GPS) receivers onEarth's ground leads to the incomplete original total electron content (TEC) maps, which are the GPS measurements of ionosphere. International global navigation satellite system (GNSS) service (IGS) TEC maps are completed with a joint effort of different observation stations involving a lot of manual work. In this work, we propose a deep learning method to learn the completion process of IGS TEC data to facilitate the TEC map completion. The proposed method can automatically recover the incomplete TEC maps with much reduced errors compared to two conventional automatic methods. Key Points: • We proposed a deep convolutional generative adversarial networks model to achieve the automatic completion of total electron content maps • Large amount of training data and Poisson blending are two important elements to achieve the superior performance of the proposed deep learning model • With 18 years of training data, the proposed deep learning model is able to recover the missing data more accurately than two traditional image inpainting methods

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.

No abstract

No abstract

No abstract