The radiation belts of the Earth, filled with energetic electrons, comprise complex and dynamic systems that pose a significant threat to a variety of satellite systems. While various models of the relativistic electron flux have been developed for geostationary orbit (GEO), the behaviour of the medium energy (120-600 keV) electrons below GEO remains poorly quantified. In this paper we present a Medium Energy electRon flux In Earth’s outer radiatioN belt (MERLIN) model based on the Light Gradient Boosting (LightGBM) machine learning algorithm. The MERLIN model takes as input the satellite position, a combination of geomagnetic indices and solar wind parameters including the time history of velocity, and does not use persistence. MERLIN is trained and validated on $>$15 years of the GPS electron flux data, and tested on more than $1.5$ years of measurements. 10-fold cross validation (CV) yields that the model predicts the MEO radiation environment well, both in terms of dynamics and amplitudes of flux. Evaluation on the test set yields high correlation between the predicted and observed electron flux (0.8) and low values of absolute error. The MERLIN model can have wide Space Weather applications, providing information for the scientific community in the form of radiation belts reconstructions, as well as industry for satellite mission design, nowcast of the MEO environment and surface charging analysis.

In recent years, feedforward neural networks (NNs) have been successfully applied to reconstruct global plasmasphere dynamics in the equatorial plane. These neural network-based models capture the large-scale dynamics of the plasmasphere, such as plume formation and erosion of the plasmasphere on the nightside. However, their performance depends strongly on the availability of training data. When the data coverage is limited or non-existent, as occurs during geomagnetic storms, the performance of NNs significantly decreases, as networks inherently cannot learn from the limited number of examples. This limitation can be overcome by employing physics-based modeling during strong geomagnetic storms. Physics-based models show a stable performance during periods of disturbed geomagnetic activity, if they are correctly initialized and configured. In this study, we illustrate how to combine the neural network- and physics-based models of the plasmasphere in an optimal way by using the data assimilation Kalman filtering. The proposed approach utilizes advantages of both neural network- and physics-based modeling and produces global plasma density reconstructions for both quiet and disturbed geomagnetic activity, including extreme geomagnetic storms. We validate the models quantitatively by comparing their output to the in-situ density measurements from RBSP-A for an 18-month out-of-sample period from 30 June 2016 to 01 January 2018, and computing performance metrics. To validate the global density reconstructions qualitatively, we compare them to the IMAGE EUV images of the He+ particle distribution in the Earth’s plasmasphere for a number of events in the past, including the Halloween storm in 2003.

We compare the predictions of the GUMICS-4 global magnetohydrodynamic model for the interaction of the solar wind with the Earth’s magnetosphere with Cluster SC3 measurements for over one year, from January 29, 2002, to February 2, 2003. In particular, we compare model predictions with the north/south component of the magnetic field (Bz) seen by the magnetometer, the component of the velocity along the Sun-Earth line (Vx), and the plasma density as determined from a top hat plasma spectrometer and the spacecraft’s potential from the electric field instrument. We select intervals in the solar wind, the magnetosheath, and the magnetosphere where these instruments provided good quality data and the model correctly predicted the region in which the spacecraft is located. We determine the location of the bow shock, the magnetopause and, the neutral sheet from the spacecraft measurements and compare these locations to those predicted by the simulation. The GUMICS-4 model agrees well with the measurements in the solar wind however its accuracy is worse in the magnetosheath. The simulation results are not realistic in the magnetosphere. The bow shock location is predicted well, however, the magnetopause location is less accurate. The neutral sheet positions are located quite accurately thanks to the special solar wind conditions when the By component of the interplanetary magnetic field is small.