Improvement of IRI Global TEC Maps by Deep Learning Based on Conditional Generative Adversarial Networks

Abstract

In this study, we make a model, which is called DeepIRI, to generate improved International Reference Ionosphere (IRI) total electron content (TEC) maps by deep learning based on conditional Generative Adversarial Networks. For this we consider 48,901 pairs of IRI TEC maps and International Global Navigation Satellite Systems (GNSS) Service (IGS) TEC maps from 2001 to 2011 for training the model. We evaluate the model by comparing IGS TEC maps and DeepIRI TEC ones from 2013 to 2017. The DeepIRI TEC maps that our model generated are much more consistent with the corresponding IGS TEC maps than the IRI TEC ones. Especially, ionospheric peak structures are successfully generated in DeepIRI TEC maps while they are not in IRI-2016 ones. From the average differences between IRI and IGS TEC maps, our model greatly improved the IRI TEC at low-latitude region around the equatorial anomaly. These results show that our model can improve the global TEC prediction ability of the IRI-2016. Our study suggests a sufficient possibility to generate DeepIRI global TEC maps in near real time if IRI is generated in time. Our approach can be applied to make improved versions of empirical models if more realistic observations are available with a time delay. Plain Language SummaryThe International Reference Ionosphere (IRI) is one of the most widely used standard models of the ionosphere. The IRI total electron content (TEC) is very important to monitor ionospheric disturbances. This paper makes a model to improve IRI TEC maps by deep learning based on conditional Generative Adversarial Networks, which is a general purpose solution to resolve image-to-image translation problems. We consider many pairs of IRI TEC maps and IGS TEC maps for training the model. Our model greatly improves the global IRI TEC maps, which are very consistent with the observations.

One‐Day Forecasting of Global TEC Using a Novel Deep Learning Model

“…Recently, Ji et al. (2020) developed an improved version of IRI TEC maps, which is called DeepIRI, by deep learning. This model can generate a global TEC map in near real time if input parameters of IRI are properly predicted.…”

“…It is difficult to forecast IGS TEC maps in real time using our model since they have a latency of 11 days. Recently, Ji et al (2020) developed an improved version of IRI TEC maps, which is called DeepIRI, by deep learning. This model can generate a global TEC LEE ET AL.…”

“…Ji et al. (2020) developed an improved IRI model by applying this method to translation from IRI TEC maps to IGS TEC maps. These studies demonstrate that such an image translation method can be successfully applied to scientific research.…”

“…Park et al (2019) successfully generated solar ultraviolet (UV) and extreme UV (EUV) images from solar magnetograms. Ji et al (2020) developed an improved IRI model by applying this method to translation from IRI TEC maps to IGS TEC maps. These studies demonstrate that such an image translation method can be successfully applied to scientific research.…”

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

“…Based on the GAN, a mess of improved GANs have shown their special capabilities with regard to the special tasks. For example, the conditional GAN (CGAN) can solve the conditional probability problems (E.un‐Young Ji et al., 2020) regardless of the complex structure which has been applied to reconstruct the cloud vertical profile (Leinonen et al., 2019). What's more, deep convolutional generative adversarial networks (DCGAN) is developed based on the success GANs, which combines the CNNs and GANs (Ledig et al., 2016).…”