Communications of the ACM
Space Weather Model Gives Earlier Warning of Satellite-Killing Radiation Storms
A machine learning computer model developed by researchers at Los Alamos National Laboratory accurately predicts damaging radiation storms caused by Van Allen belts up to two days in advance.
Credit: Los Alamos National Laboratory
Researchers at Los Alamos National Laboratory have developed a new machine learning computer model that accurately predicts damaging radiation storms caused by Van Allen belts—zones of energetic charged particles, most of which originate from the solar wind, that are captured by and held around a planet by that planet's magnetic field—two days before the storm.
The PreMevE 2.0 predictive model builds on a previous model that successfully predicted radiation storms one day in advance.
PreMevE 2.0 improves forecasts by incorporating upstream solar wind speeds. It can predict future events by training on existing data sets from the U.S. National Oceanic and Atmospheric Administration (NOAA) and Los Alamos satellites to learn important patterns of electron behavior.
The model's machine learning framework can also be applied to other systems that use time-based measurements, such as capturing earthquake patterns among large volumes of seismic time-series data.
From Los Alamos National Laboratory News
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found