Modeling Equatorial to Mid-Latitudinal Global Night Time Ionospheric Plasma Irregularities Using Machine Learning

This study focuses on modeling the characteristics of nighttime topside Ionospheric Plasma Irregularities (PI) on a global scale. We utilize Random Forest (RF) and a one-dimensional Convolutional Neural Network (1D-CNN) model, incorporating data from the Swarm A, B, and C satellites, space weather data from the OMNIWeb data center, as well as zonal and meridional wind model data. Our objective is to simulate monthly global PI characteristics using a multilayer 1D-CNN model trained on 12 space weather and ionospheric parameters. In addition, we investigate the most influential input parameters for predicting global nighttime PI characteristics. Our findings indicate that non-equinox months exhibit the highest equatorial PI magnitude over the American-African longitudinal sector, contrary to the expected higher Rayleigh-Taylor instability growth rate during equinox months. Winter months display the most intense and widespread vertically and horizontally distributed equatorial PI patterns. We also observe double peaks across geomagnetic latitudes and longitudinally varying wavelike irregularity structures, particularly in May, August, and predominantly in September. Furthermore, north-south hemispherical asymmetry in PI observed across different seasons. Through the RF parameter importance analysis method, we determine that temporal, geographical, and magnetic disturbance-related factors play a crucial role in predicting global PI variabilities. These findings emphasize the significance of these variables in controlling the strongest PI characteristics observed in the Atlantic sector, which has garnered considerable attention in PI research. The employed 1D-CNN model demonstrates exceptional predictive capabilities, exhibiting a strong correlation of 0.98 for global PI characteristics across all months and satellites. This study aimed to understand the characteristics of nighttime Ionospheric Plasma Irregularities (PI) on a global scale. To achieve this, we used advanced machine learning techniques called RF and a one-dimensional Convolutional Neural Network (1D-CNN). We collected data from the Swarm A, B, and C satellites, as well as space weather data and wind model data. The goal is to create a model that could simulate monthly global PI characteristics using 12 different space weather and ionospheric parameters. We found that during non-equinox months, the equatorial PI magnitude is highest over the American-African longitudinal sector. It is expected that the equinox months would have a higher growth rate of Rayleigh-Taylor instability (RTI). We also observed that winter months had the most intense and widespread equatorial PI patterns, both vertically and horizontally distributed. Across different seasons, we noticed a north-south hemispherical asymmetry in PI. We also identified specific months where double peaks observed across geomagnetic latitudes and irregularity structures that varied along longitudes, particularly in May, August, and mainly in September. Using the RF parameter importance analysis method, we determined that factors related to time, location, and magnetic disturbances played a crucial role in predicting global PI variabilities. These findings highlight the importance of these variables in controlling the strongest PI characteristics observed in the Atlantic sector, which is an area of significant interest in PI research. The 1D-CNN model used in this study demonstrated exceptional predictive capabilities, showing a strong correlation of 0.98 for global PI characteristics across all months and satellites. This suggests that the model is highly reliable in simulating and predicting PI behavior on a global scale. Winter months exhibit the most intense and widespread vertically and horizontally dispersed PI patterns simultaneously on all the three Swarm satellites The 1D-CNN model demonstrates remarkable predictive capabilities, with a strong correlation of 0.98 for all global PI characteristics Temporal, geographical, and factors related to magnetic disturbance were found to play a crucial role on PI occurrence based on Random Forest importance score