Atmospheric neutral density is a crucial component to accurately predicting and tracking the motion of satellites. During periods of elevated solar and geomagnetic activity atmospheric neutral density becomes highly variable and dynamic. This variability and enhanced dynamics make it difficult to accurately model neutral density leading to increased errors which propagate from neutral density models through to orbit propagation models. In this paper we investigate the dynamics of neutral density during geomagnetic storms. We use a combination of solar and geomagnetic variables to develop three Random Forest machine learning models of neutral density. These models are based on (1) slow solar indices, (2) high cadence solar irradiance, and (3) combined high-cadence solar irradiance and geomagnetic indices. During quiet-times all three models perform well; however, during geomagnetic storms the combined high cadence solar iradiance/geomagnetic model performs significantly better than the models based solely on solar activity. Overall, this work demonstrates the importance of including geomagnetic activity in the modeling of atmospheric density and serves as a proof of concept for using machine learning algorithms to model, and in the future forecast atmospheric density for operational use.

Precipitation into the atmosphere is one of the main processes by which high energy electrons trapped in Earth’s inner magnetosphere are lost from the system. Precipitating electrons can affect the chemical composition of the atmosphere and provide insight into the complex dynamics of the Van Allen radiation belts. This study compares energetic electron precipitation measurements at low-Earth-orbit by the Focused Investigations of Relativistic Electron Burst Intensity, Range, and Dynamics (FIREBIRD-II) CubeSats with NOAA Polar-orbiting Operational Environmental Satellite (POES) and ESA Meteorological Operational satellite (MetOp) satellites, which are equipped with the Medium-Energy Proton Electron Detector (MEPED). The analysis considers 51 high quality conjunction events during times of low to moderate geomagnetic activity. The spacecraft capture similar electron flux variability, and FIREBIRD-II observations fall between POES/MetOp 0 and 90 degree telescopes, likely a result of FIREBIRD-II sampling both precipitating and mirrored electrons due to uncertainties in pointing direction. Results demonstrate the value of high-resolution differential energy observations of electron precipitation by low-cost CubeSats such as FIREBIRD-II, especially during periods of low flux.