NASA's New AI Model Can Provide Advance Warning of Impending Solar Storms

NASA's Solar Dynamics Observatory captures a solar flare and burst of solar material erupting into space on Oct. 2, 2014. Credit: NASA/SDO 

March 30, 2023


NASA has developed a new computer model that uses artificial intelligence (AI) to analyze spacecraft measurements of the solar wind and predict where an impending solar storm will strike on Earth, with 30 minutes of advance warning. The model, called DAGGER (Deep Learning Geomagnetic Perturbation), provides just enough time to prepare for these storms and prevent severe impacts on power grids and other critical infrastructure. The risk of geomagnetic storms and devastating effects on society is presently increasing as we approach the next “solar maximum” – a peak in the Sun’s 11-year activity cycle – which is expected to arrive sometime in 2025. The DAGGER team tested the model against two geomagnetic storms that happened in August 2011 and March 2015, and it was able to quickly and accurately forecast the storm’s impacts around the world. The researchers applied deep learning, which trains computers to recognize patterns based on previous examples, to identify relationships between solar wind measurements from heliophysics missions and geomagnetic perturbations observed at ground stations across the planet. DAGGER is the first model to combine the swift analysis of AI with real measurements.

According to the researchers, the new computer model, DAGGER, represents a significant improvement over previous prediction models. While previous models have provided local forecasts for specific regions or global predictions that were not very timely, DAGGER uses deep learning to quickly analyze real measurements of the solar wind and predict where a solar storm will hit anywhere on Earth, with just 30 minutes of advance warning.

The researchers at the Frontier Development Lab developed DAGGER by applying deep learning to identify connections between the solar wind and geomagnetic perturbations that cause disruption to technology. They used solar wind measurements from a range of heliophysics missions, including ACE, Wind, IMP-8, and Geotail, and analyzed the data to identify patterns that could predict impending solar storms.

The model's predictions are generated in less than a second and update every minute. DAGGER is the first model to combine the swift analysis of AI with real measurements, allowing it to provide global predictions that are both timely and accurate. The researchers believe that DAGGER could provide crucial advance warning to prepare for solar storms and prevent severe impacts on critical infrastructure.

The risk of severe solar storms and the devastating effects they can have on our society is increasing as we approach the next solar maximum, which is expected to arrive sometime in 2025. The ability to predict solar storms with just 30 minutes of advance warning could be critical in preventing widespread electrical disruptions, persistent blackouts, and interruptions to global communications.

In addition to its potential for disaster prevention, DAGGER could also have important applications for space exploration. As humans venture further into space, they will need to be prepared for the effects of solar storms on their equipment and technology. The ability to predict these storms in advance could be essential to ensure the safety and success of future space missions.

Overall, the development of DAGGER represents a significant step forward in our ability to predict and prepare for solar storms. With the potential to provide critical advance warning, DAGGER could help prevent widespread disruption and damage caused by solar storms, protecting our society and infrastructure.