Specifying High-altitude Electrons using Low-altitude LEO Systems: The SHELLS Model

We describe an artificial neural network model of the near-Earth space radiation environment. Geomagnetic indices and LEO electron flux measurements from the NOAA POES spacecraft are used as model training inputs. MagEIS electron fluxes from NASA's Van Allen Probes spacecraft form the training outputs. Initial results are presented demonstrating that the model can accurately specify outer radiation belt (L 3-7) electron fluxes over a wide energy range, from 300 keV to 2 MeV. The model thus allows the user to extract the current and historical internal charging hazard due to these electrons across any user-specified orbit through the outer belt. We discuss how this empirical model of relativistic electrons in the outer radiation belt can be used to benchmark physics-based, data-assimilative, and other models used for environmental forecasting.