Ionospheric structure usually changes dramatically during a strong geomagnetic storm period, which will significantly affect the short-wave communication and satellite navigation systems. It is critically important to make accurate ionospheric predictions under the extreme space weather conditions. However, ionospheric prediction is always a challenge, and pure physical methods often fail to get a satisfactory result since the ionospheric behavior varies greatly with different geomagnetic storms. In this paper, in order to find an effective prediction method, one traditional mathematical method (autoregressive integrated moving average—ARIMA) and two deep learning algorithms (long short-term memory—LSTM and sequence-to-sequence—Seq2Seq) are investigated for the short-term predictions of ionospheric TEC (Total Electron Content) under different geomagnetic storm conditions based on the MIT (Massachusetts Institute of Technology) madrigal observation from 2001 to 2016. Under the extreme condition, the performance limitation of these methods can be found. When the storm is stronger, the effective prediction horizon of the methods will be shorter. The statistical analysis shows that the LSTM can achieve the best prediction accuracy and is robust for the accurate trend prediction of the strong geomagnetic storms. In contrast, ARIMA and Seq2Seq have relatively poor performance for the prediction of the strong geomagnetic storms. This study brings new insights to the deep learning applications in the space weather forecast.

Energetic electrons have frequently been observed in small‐scale flux ropes. However, whether these energetic electrons were energized directly within the flux rope or not is unknown. In this paper, we present concrete evidence provided by the Magnetospheric Multiscale mission that a secondary flux rope provided strong acceleration for electrons expelled by the reconnection X line. We find that the energetic electron fluxes inside the ion‐scale flux rope were larger than those outside the flux rope. Electrons were adiabatically accelerated by betatron and Fermi mechanisms inside the flux rope. The highest energy electrons (>100 keV) were produced by betatron acceleration, whereas Fermi acceleration was unable to accelerate the electrons to high energy probably due to the finite distance of the acceleration region along the field‐aligned direction. These results confirm the essential role of ion‐scale flux ropes in producing energetic electrons.

Dipolarization fronts (DFs) are important for energy conversion, particle acceleration, and flux transport in the magnetotail. The partition of energy conversion between ions and electrons and the energy dissipation at DFs are not well understood. In this paper, we present a statistical study of energy conversion and dissipation of 122 DFs observed by Magnetospheric Multiscale mission in the magnetotail. Statistically, electromagnetic energy transfers to plasma at DF. The released energy is mainly transferred to ions rather than electrons. On average, ions gain energy across the whole DF, while electrons gain energy at the leading part but lose energy at the trailing part of DFs. Joule dissipation J · (E+v_e × B) can be either positive or negative at DFs, and its average value is very small. The kinetic energy dissipation parameter Pi − D does not exhibit clear signatures at the DFs; hence, it is not suitable for quantifying the energy dissipation at DF.

Secondary flux ropes are suggested to play important roles in energy dissipation and particle acceleration during magnetic reconnection. However, their generation mechanism is not fully understood. In this Letter, we present the first direct evidence that a secondary flux rope was generated due to the evolution of an electron vortex, which was driven by the electron Kelvin-Helmholtz instability in an ion diffusion region as observed by the Magnetospheric Multiscale mission. The subion scale (less than the ion inertial length) flux rope was embedded within the electron vortex, which contained a secondary electron diffusion region at the trailing edge of the flux rope. We propose that intense electron shear flow produced by reconnection generated the electron Kelvin-Helmholtz vortex, which induced a secondary reconnection in the exhaust of the primary $X$ line and then led to the formation of the flux rope. This result strongly suggests that secondary electron Kelvin-Helmholtz instability is important for reconnection dynamics.

Solar flare formation mechanisms and their corresponding predictions have commonly been difficult topics in solar physics for decades. The traditional forecasting method manually constructs a statistical relationship between the measured values of solar active regions and solar flares that cannot fully utilize the information related to solar flares contained in observational data. In this article, we first used neural-network methods driven by the measured magnetogram and magnetic characteristic parameters of the sunspot group to learn the prediction model and predict solar flares. The prediction fusion model is based on a deep neural network, convolutional neural network, and bidirectional long short-term memory neural network and can predict whether a sunspot group will have a flare event above class M or class C in the next 24 or 48 hr. The real skill statistics (TSS) and F1 scores were used to evaluate the performances of our fusion model. The test results clearly show that this fusion model can make full use of the information related to solar flares and combine the advantages of each independent model to capture the evolution characteristics of solar flares, which is a much better performance than traditional statistical prediction models or any single machine-learning method. We also proposed two frameworks, namely F1_FFM and TSS_FFM, which optimize the F1 score and TSS score, respectively. The cross validation results show that they have their respective advantages in the F1 score and TSS score.

The scattering enhancement technique has shown prominent potential in various regimes such as satellite communication, Radar Cross Section (RCS) camouflage, and remote sensing. Currently, the scattering enhancement devices based on the metasurface have shown advantages in light weight and better performance. These metasurfaces always possess complex structure, it is hard to achieve through the tradition trial-and-error method which relies on the full-wave numerical simulation. In this paper, a new method combining the machine learning and the evolution optimization algorithm is proposed to design the metasurface retroreflector (MRF) for arbitrary direction incident wave. In this method, a predicting model and a generative inverse design model are constructed and trained, the predicting model is used to evaluate the fitness of each offspring in the genetic algorithm (GA), the generative model is used to initialize the first offspring of the GA by inverse generate the MRF based on the requirements of the designer. With the assistance of these two machine learning models, the evolution optimization algorithm is employed to find the optimal design of the MRF. This approach enables automatic solution of electromagnetic inverse design problems and opens the way to facilitate the optimization of other metadevices.