Using new observations from the Chinese Meridian Project (CMP), this study examines the characteristics of neutral winds in the East Asian sector during the Mother's Day super‐intense storm in May 2024, primarily focusing on its effects on the disturbances over China and adjacent areas. It is the first time that new measurements from three Dual‐Channel Optical Interferometers (DCOIs) are utilized to analyze storm‐time neutral winds at an altitude of 250 km in northern China. By developing all northern‐hemisphere Super Dual Auroral Radar Network radars including six Chinese Dual Auroral Radar Network (CN‐DARN) radars, the newly derived ionospheric convection pattern and its impacts on neutral winds can be well analyzed. The results show that a strong equatorward wind with a maximum amplitude of ∼400 m/s in the meridional component was observed for the first time during the storm main phase. In the East Asian sector, a negative ionospheric storm over China and adjacent areas was accompanied by this enhancement in equatorward wind in the night of May 10. Additionally, ionospheric convection expanded to 43° magnetic latitude (MLAT) with eastward ion velocities exceeding 800 m/s around 50° MLAT. This can strengthen zonal wind in northern China, producing a notable eastward surge of ∼230 m/s measured by new DCOIs in the dawnside sub‐auroral region. Wave‐like oscillations in neutral winds were observed by multi‐DCOI stations, which were associated with the storm‐time Traveling Atmospheric Disturbances (TADs). During the storm recovery phase, a high‐level total electron content cluster shifted from eastern China to the central regions, which may be attributed to enhanced ∑[O]/[N₂].

Recently, although various deep learning techniques have been applied to building space weather prediction models, a large amount of relevant prior knowledge of solar eruptions and magnetic properties is ignored during the model development. By integrating prior knowledge in flare production into the convolutional neural network (CNN) structures, we have developed a knowledge‐informed deep neural network model aiming at forecasting solar flares. The line‐of‐sight magnetograms of Space‐weather HMI Active Region Patches (SHARP) from May 2010 to December 2018 are selected. We have surveyed the relationships between solar flares and both the active region (AR) area and magnetic type. When integrating prior knowledge into the CNNs, three aspects are considered: (a) keeping the magnetic structure unchanged (data preprocessing) while filling SHARP magnetograms into squares, (b) grouping the data samples into two subsets according to different flare productivities (sample grouping), and (c) adding AR area as an extra input parameter to the CNN (extra input parameter implementation). Pure CNN model, Fusion model 1, and Fusion model 2 are built to forecast M‐class or above flares in the next 48 hr, which involve data preprocessing, data preprocessing and sample grouping, and all the three aspects, respectively. Fusion model 2 that augments the most prior knowledge has the best performance. Our results imply that prior knowledge can play an important role in building deep learning flare forecasting models. In the future, adopting knowledge‐informed deep neural networks will be an effective way to further improve the forecasting performance for other space weather events.

The Earth's ionosphere plays a critical role in radio wave transmission, reflection, and scattering, directly affecting communication, navigation, and positioning systems. However, the comprehensive impacts of space weather remain to be fully established in cases where the ionosphere experiences strong disturbances during geomagnetic storms. We reported unprecedented observational evidence of extreme ionospheric electron density depletion and its hemispheric asymmetry during the May 10–12, 2024 super geomagnetic storm, utilizing multi-instrument ground-based and spaceborne in-situ observations. The ionospheric electron density significantly decreased, with a maximum reduction of 98% over the whole northern hemisphere for more than 2 days, causing backscatter echo failures in multiple ionosondes within the Chinese Meridian Project (CMP) monitoring network. In contrast, mid-to-low latitude regions in the southern hemisphere exhibited electron density enhancements. Thermosphere-Ionosphere-Electrodynamics General Circulation Model (TIEGCM) simulations demonstrated strong consistency with northern hemispheric observations. The vertical drift and the column integrated ratio of O and N2 (ΣO/N2) from observations and simulations indicated the deep reduction of total electron content (TEC) mainly generated by severe ion recombination associated with neutral composition changes that interacted with the disturbed electric field. The summer to winter neutral wind and asymmetry of O/N₂ were possibly responsible for the asymmetry in electron density between the northern and southern hemispheres. These results advance understanding of ionospheric storm physics by establishing causal links between magnetosphere-thermosphere coupling processes and extreme electron density variations, while providing critical observational constraints for space weather model refinement.

We investigate the thermosphere latitudinal response to Joule heating from 265 geomagnetic storms during the period of January 2002 to December 2008. The total mass density enhancements at 400 km are derived from the Challenging Minisatellite Payload (CHAMP) and the Gravity Recovery and Climate Experiment (GRACE) satellites with temporal and spatial coverage. We examine Joule heating and its influence on the thermospheric density using data from the Defense Meteorological Satellite Program (DMSP) spacecraft and Weimer‐2001 electric potential model for storms. The results show that during geomagnetic storms, Joule heating can cause the thermospheric density to enhance in the higher‐latitude areas. In addition, during weak and moderate geomagnetic storms, the difference in the latitude corresponding to strong Joule heating with the latitude where high‐latitude thermospheric density enhances is only 0°–10° latitudes, while increases to 10°–15° for the intense storms. Besides, it is found that the peak density enhancement in LT is closer to peak Joule heating for more intense geomagnetic storms.

The responses of thermospheric densities to geomagnetic activity indices and Joule heating are analyzed during 265 geomagnetic storms and can be used to calibrate the model NRLMSISE‐00 with neutral mass density observed at 400 km based on the CHAMP satellite from 2002 to 2008. In this work, the geomagnetic activities at high and low latitudes are identified by AE indices and Dst indices. During geomagnetic storms, Joule heating and its impacts on the thermospheric density are calculated by the Weimer‐2001 electric potential model and the DMSP spacecraft. The results show that the response of thermospheric density to both AE and Dst index takes a longer time as geomagnetic storms intensify. During weak and moderate storms, density delays AE indices for about 0–1 hr, while it is 2–4 hr for intense storms. In addition, the time differences between Dst indices and AE indices increase as storms intensify. During weak and moderate geomagnetic storms, the difference in the time corresponding to Dst indices with the time when AE indices peak is only 1–2 hr, while it increases to 3–5 hr for the intense storms. Furthermore, the calibration of the NRLMSISE‐00 model results can reproduce the storm‐time thermospheric density well, with the Mean Relative Error (MRE) between density observation and model decreasing from 40% to 10% after the correction.