NASA is working on a project that aims to predict the effects of solar flares on Earth’s systems. The project, called DAGGER (Deep leArninG Geomagnetic pErtuRbation), is a joint effort between NASA, the US Geological Survey, and the Department of Energy at the Frontier Development Lab. DAGGER uses machine learning to identify patterns in data collected from multiple satellites monitoring the sun and ground stations watching for geomagnetic disruptions. The resulting system can quickly and accurately forecast the effects of solar flares across the globe, combining the strengths of previous approaches while avoiding their disadvantages. DAGGER is the first model to combine the swift analysis of AI with real measurements from space and across Earth to generate frequently updated predictions that are both prompt and precise for sites worldwide.
Solar flares can cause disruptions in Earth’s systems, including electronics and infrastructure. Solar wind, an unrelenting stream of material from the sun, is normally absorbed or dissipated by our magnetosphere. However, during a solar storm, the stream may be intense enough to overwhelm the local defenses, causing disruptions in technology. Even telegraph stations were not safe during the largest on-record solar storm, 1859’s Carrington Event. While we cannot stop these stellar events from occurring, we can better prepare for them if we know they are coming.
NASA’s job includes understanding and predicting space weather. Since there is no air in space, we rely on a set of satellites to detect and relay important data to us. One such measurement is of solar wind. NASA has described it as “an unrelenting stream of material from the sun.” The team behind DAGGER collected data on solar flares from multiple satellites monitoring the sun and ground stations watching for geomagnetic disruptions. The deep learning model they designed identified patterns in how solar flares lead to geomagnetic perturbations.
Using geomagnetic storms that hit Earth in 2011 and 2015 as test data, the team found that DAGGER was able to quickly and accurately forecast their effects across the globe. This could make a big difference when we know there’s vulnerable infrastructure that could suddenly shut down. A few minutes’ warning is better than none! While it may be a bit before you get a solar alert on your phone telling you to pull over or your car might stop working (this won’t actually happen…probably), the DAGGER model could help us better prepare for the effects of solar flares on Earth’s systems.
The DAGGER model is open source, and you can read the paper describing it in this issue of the journal Space Weather. Understanding and predicting space weather is an important part of NASA’s job, and DAGGER is a promising step towards better preparation for the effects of solar flares on Earth’s systems.