Observations with a global coverage are very important for space physics research and space weather monitoring. However, due to the technical limitations, it would be very expensive or even impossible to achieve a seamless global coverage even with advanced observational devices. It would be useful to fill missing data gaps to create a global map from the available data, but up until now this has been very challenging. Fortunately, the deep learning method, a recent breakthrough in artificial intelligence, may provide an effective way to solve this problem by making full use of data from reliable observations. In this paper, a promising deep learning algorithm, deep convolutional generative adversarial network (DCGAN), is investigated to fill the missing data of total electron content (TEC) map images. The direct use of DCGAN fails to fill missing data for the completion of TEC maps because there are always missing TEC data in some regions, such as oceans, where the features vary with time and geophysical conditions. Thus, no useful information can be utilized by DCGAN to achieve a meaningful image completion. In order to overcome this shortcoming of the original DCGAN method, a novel regularized DCGAN (R‐DCGAN) is proposed by adding an extra discriminator and some widely used reference TEC maps from the International Global Navigation Satellite Systems Service Ionosphere Working Group. The proposed R‐DCGAN method generates satisfactory ionospheric peak structures at different times and geomagnetic conditions, which demonstrate its effectiveness on filling the missing data in TEC maps. The proposed R‐DCGAN framework can be readily extended to a broad application in other fields of space sciences, particularly for addressing the missing observation data issues.

Low-dose computed tomography (LDCT) is desired due to prevalence and ionizing radiation of CT, but suffers elevated noise. To improve LDCT image quality, an image-domain denoising method based on cycle-consistent generative adversarial network (CycleGAN) is developed and compared with two other variants, IdentityGAN and GAN-CIRCLE. Different from supervised deep learning methods, these unpaired methods can effectively learn image translation from the low-dose domain to the full-dose (FD) domain without the need of aligning FDCT and LDCT images. The results on real and synthetic patient CT data show that these methods can achieve peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) comparable to, if not better than, the other state-of-the-art denoising methods. Among CycleGAN, IdentityGAN, and GAN-CIRCLE, the later achieves the best denoising performance with the shortest computation time. Subsequently, GAN-CIRCLE is used to demonstrate that the increasing number of training patches and of training patients can improve denoising performance. Finally, two nonoverlapping experiments, i.e., no counterparts of FDCT and LDCT images in the training data, further demonstrate the effectiveness of unpaired learning methods. This work paves the way for applying unpaired deep learning methods to enhance LDCT images without requiring aligned FD and low-dose images from the same patient.

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.

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.