In this paper, a deep learning long-short-term memory (LSTM) method is applied to the forecasting of the critical frequency of the ionosphere F2 layer (foF2). Hourly values of foF2 from 10 ionospheric stations in China and Australia (based on availability) from 2006 to 2019 are used for training and verifying. While 2015 and 2019 are exclusive for verifying the forecasting accuracy. The inputs of the LSTM model are sequential data for the previous values, which include local time (LT), day number, solar zenith angle, the sunspot number (SSN), the daily F10.7 solar flux, geomagnetic the Ap and Kp indices, geographic coordinates, neutral winds, and the observed value of foF2 at the previous moment. To evaluate the forecasting ability of the deep learning LSTM model, two different neural network forecasting models: a back-propagation neural network (BPNN) and a genetic algorithm optimized backpropagation neural network (GABP) were established for comparative analysis. The foF2 parameters were forecasted under geomagnetic quiet and geomagnetic disturbed conditions during solar activity maximum (2015) and minimum (2019), respectively. The forecasting results of these models are compared with those of the international reference ionosphere model (IRI2016) and the measurements. The diurnal and seasonal variations of foF2 for the 4 models were compared and analyzed from 8 selected verification stations. The forecasting results reveal that the deep learning LSTM model presents the optimal performance of all models in forecasting the time series of foF2, while the IRI2016 model has the poorest forecasting performance, and the BPNN model and GABP model are between two of them.

This paper compares the wind fields measured by the meteor radar at Mohe, Beijing, Wuhan, and Sanya stations and horizontal wind model (HWM14) predictions. HWM14 appears to successfully reproduce the height-time distribution of the monthly mean zonal winds, although large discrepancies occur in wind speed between the model and measurement, especially in the summer and winter months. For meridional wind, the consistency between model prediction and radar observation is worse than that of zonal wind. The consistency between radar measurements and model prediction at Sanya station is worse than other sites located at higher latitudes. Harmonic analysis reveals large discrepancies in diurnal, semidiurnal, and terdiurnal tides extracted from meteor radar observations and HWM14 predictions.

A longitudinal chain and a latitudinal chain of ionosondes, located at Yakutsk (129.60°E, 62.00°N), Mohe (122.37°E, 53.50°N), Beijing (116.25°E, 40.25°N), Wuhan (114.61°E, 30.53°N), Sanya (109.42°E, 18.34°N), I‐Cheon (127.54°E, 37.14°N), San Vito (17.80°E, 40.60°N), Roquest (0.50°E, 40.80°N), Millstone Hill (71.50°W, 42.60°N), and Alpena (83.56°W, 45.07°N) ionosondes, are utilized to statistically investigate the sporadic E layer (Es) occurrence rate and variation. The Es occurrence rates at all stations show a similar dependence on local time and season. However, the seasonal dependence of Es occurrence is more distinct at middle latitudes than that at low latitudes along the 120°E longitude. Results at different stations along ∼40°N latitude show much lower Es occurrence at the American sector than that at European and East Asian sectors, which is most likely because the horizontal geomagnetic field in north America is smaller than in other regions. The statistical results demonstrate that the seasonal variations of Es occurrence and strength are related to the annual variation of meteor counts. Simulation results show that the summer maximum of the ion vertical drift velocity driven by the variations of neutral densities and winds could also contribute to the seasonal variations of Es occurrence and intensity. The seasonal variations of the quasi‐6‐day and quasi‐16‐day oscillations in Es are also investigated. The seasonal variations of periodic disturbances of the Es differ between each station. Planetary waves in the MLT region cannot fully explain the seasonal variations of the periodic disturbance of Es. Solar and geomagnetic activities can also result in periodic variations of the Es.

This study investigates the variations of middle and low latitude sporadic-E (Es) layers in response to a geomagnetic storm. Es layers are observed by five ionosondes located in the Eastern Asian sector. The critical frequencies of Es layers (foEs) at six stations increased in sequence from high latitude stations to low latitude stations after IMF/Bz turning southward. Lomb–Scargle analysis shows the amplification of semidiurnal oscillation amplitude in the vertical height of Es layers during geomagnetic disturbance. Modeling results of the NCAR Thermosphere-Ionosphere-Electrodynamics General Circulation Model (TIEGCM) show the enhancement of the wind field in the mesosphere and the lower thermosphere (MLT) region. Our study provides evidence that the enhanced wind field in the MLT region during the storm period could result in the enhancement of Es layers at middle and low latitude.