Updates to a machine-learning computer model that accurately predicts radiation storms caused by the Van Allen belts give researchers more reliable two-day forecasts of the satellite-damaging radiation storms. The research was published in “Space Weather.”
“Our latest update to the predictive model for megaelectron‐volt (MeV) electrons inside the Earth's outer radiation belt focuses on forecasting ultra-relativistic electron flux distributions across the outer radiation belt,” said Yue Chen (ISR-1).
High-speed electrons inside Earth's outer Van Allen belt pose a major radiation threat to satellites by disrupting their electronic components. These electrons, especially those traveling at nearly the speed of light, are of particular interest due to their high-penetrating ability; these are sometimes called killer electrons. Because of this, forecasting ultra-relativistic electrons is important to all space sectors. For example, satellites operate in orbits with high-altitude apogees are prone to severe radiation storms of killer electrons, including the navigation satellites such as GPS and communication satellites in geosynchronous orbit
This predictive model for MeV electrons inside the Earth’s outer Van Allen belt builds on a previously successful model. The new model, called PreMevE-2E, makes forecasts driven by observations in low-Earth-orbits by National Oceanic and Atmospheric Administration (NOAA) satellites, upstream solar wind conditions from solar wind monitors, and ultra-relativistic electrons measured by one Los Alamos geostationary orbit (GEO) satellite.
2 days’ notice
Using data from NASA’s Van Allen Probes mission, the research team evaluated 32 supervised machine-learning models in four different machine learning classes, introduce the ensemble forecasting technique, and successfully demonstrated the performance of the model. This new PreMevE-2E model can predict incoming nearly-light-speed electrons up to two days advance with high statistical fidelity.