The accurate prediction of ionospheric Total Electron Content (TEC) is important for global navigation satellite systems (GNSS), satellite communications and other space communications applications. In this study, a prediction model of global IGS‐TEC maps are established based on testing several different long short‐term memory (LSTM) network (LSTM)‐based algorithms to explore a direction that can effectively alleviate the increasing error with prediction time. We find that a Multi‐step auxiliary algorithm based prediction model performs best. It can effectively predict the global ionospheric IGS‐TEC in the next 6 days (the mean absolute deviation (MAD) and root mean square error (RMSE) are 2.485 and 3.511 TECU, respectively) compared to the IRI (the MAD and RMSE are 4.248 and 5.593 TECU). The analyses of four geomagnetic storm events are completely separate from the time range of the training set, so as to further validate the performance of the model. The International Reference Ionosphere model is used as a reference for the performance of our predictive model, and a rotated persistence is estimated by time‐shift algorithm of IGS‐TEC. The result suggests that the Multi‐step auxiliary prediction model has a good generalization performance and can have a relatively good stability and low error during a geomagnetic storm and quiet time.

The accurate prediction of storm‐time thermospheric mass density is always critically important and also a challenge. In this paper, an available prediction model is established by Long Short‐Term Memory (LSTM)‐based ensemble learning algorithms. However, the generalization ability of the deep learning model is often suspicious since training data and testing data are from the same data set in the conventional method. Therefore, in order to objectively validate the performance and generalization of the model, we utilize the GOCE data for training and the SWARM‐C data for testing to verify its performance mainly during the geomagnetic storm period. The results show that the LSTM‐based ensemble learning model (LELM) is robust under different geomagnetic activity levels and has good generalization ability for the different satellite data set. The prediction accuracy of the LELM is proved to be better than a common‐used empirical model (NRLMSISE‐00). Thus, our approach provides a promising way to give reliable and stable predictions of thermospheric mass density.

A survey of electrons with energies between ∼1 eV and 30 keV was conducted using measurements from the THEMIS spacecraft over radial distances between 3 and 12 Earth radii. Two distinct populations are observed, one with a peak energy near 10 eV and one at approximately 1 keV. These populations are present 88% of the time in the magnetosphere. The warm population (∼10 eV) is generally more dense (∼1 cm⁻³) and extends across the dayside. These warm electron characteristics are similar to the ion warm plasma cloak. The hot distribution (∼1 keV) peaks in number density (∼0.2 cm⁻³) near midnight and into the morning sector. Since the populations are transported through different evolutionary paths, there are spatial regions within the magnetosphere where the density ratio of the populations (warm to hot, n_w/n_h) is much larger or smaller than unity. At L shells greater than ∼6, near midnight and into the dawn sector, the density of the hot population is close to a factor of 10 larger than the warm populations. In other regions, the warm electron population is typically slightly more dense (∼2×) than the hot population.

Timely, reliable and comprehensive global observation information is essential for space weather research. However, limited observation technology hinders the consecutive global coverage of observation data. For the integrity and continuity of the global observation data, deep learning can obtain a global Ionospheric total electron content (TEC) map by fusing multi‐source TEC maps. Different from the previous methods, in the study, a deep learning hybrid model (RFGAN) based on Dual‐Discriminator Conditional Generative Adversarial Network (DDcGAN) and Free‐Form Image Inpainting with Gated Convolution (Deepfill v2) is proposed to fuse the Massachusetts Institute of Technology (MIT)—TEC, International Global Navigation Satellite System TEC (IGS‐TEC) and altimetry satellite TEC. Throughout the RFGAN structure, we use an autoencoder model with gated convolution to inpaint the missing parts of MIT‐TEC and altimetry satellite TEC. Meanwhile, DDcGAN fuses the inpainted MIT‐TEC (MIT'‐TEC) and IGS‐TEC to get a global TEC map with high accuracy. To a certain extent, we inpainted the ocean area of MIT‐TEC through RFGAN. At the same time, RFGAN keeps the consistency of RFGAN‐TEC and MIT‐TEC in the continent area. Our proposed deep learning hybrid model can be easily extended and widely applied to other fields of space science, especially in addressing observational data loss and multi‐source data fusion.

We analyze an energetic electron flux enhancement event in the inner radiation belt observed by Van Allen Probes during an intense geomagnetic storm. The energetic electron flux at L~1.5 increased by a factor of 3 with pronounced butterfly pitch angle distributions (PADs). Using a three‐dimensional radiation belt model, we simulate the electron evolution under the impact of radial diffusion, local wave‐particle interactions including hiss, very low frequency transmitters, and magnetosonic waves, as well as Coulomb scattering. Consistency between observation and simulation suggests that inward radial diffusion plays a dominant role in accelerating electrons up to 900 keV and transporting the butterfly PADs from higher L shells to form the butterfly PADs at L~1.5. However, local wave‐particle interactions also contribute to drive butterfly PADs at L ≳ 1.9. Our study provides a feasible mechanism to explain the electron flux enhancement in the inner belt and the persistent presence of the butterfly PADs at L~1.5.

We report the quasi‐periodic whistler‐mode waves corresponding to electron temperature anisotropy T_⊥/T_// < 1 at the center of a macroscale magnetic hole (MH) near the Earth's magnetopause observed by the Magnetospheric Multiscale mission. A significant ultra‐low frequency (ULF) wave of background magnetic field was observed in this MH. The ULF wave dramatically exacerbates the evolution of MH and the formation of the donut‐shaped electron pitch angle distribution (PAD) in the macroscale MH. When the whistler‐mode waves were generated, they are consistent with troughs of the ULF wave and density increases, which is also related to the butterfly type PAD at those moments. The analysis of dispersion relation and cyclotron resonance condition indicate that whistler‐mode waves were mainly generated by the butterfly type PAD of electrons. Our results provides new insights into one possible excitation mechanism of whistler‐mode wave.