As humanity looks to the Moon and stars for future exploration, predicting space weather — conditions in space primarily driven by the Sun — is more important than ever. 

Now, a team of astrophysicists and data scientists with NASA’s COFFIES (Consequence Of Fields and Flows in the Interior and Exterior of the Sun) has developed a novel machine-learning model capable of predicting the emergence of active regions on the Sun up to 12 hours before they appear. 

The Sun is constantly churning. Intense concentrations of localized magnetic fields can suddenly break through the solar surface, forming sunspots. Space weather forecasters then collectively number and track sunspots since they are visible manifestations of active regions, which serve as the main engines behind severe space weather events such as solar flares and coronal mass ejections. These eruptions send waves of high-energy radiation and charged particles across space, creating storms that can threaten astronauts, disable satellites, and disrupt radio communications on Earth. 

By bridging expertise across different scientific institutions, COFFIES, a NASA DRIVE (Diversify, Realize, Integrate, Venture, Educate) Science Center, brought together a team of researchers from New Jersey Institute of Technology (NJIT), Princeton University, and NASA’s Ames Research Center in California’s Silicon Valley. The team turned to advanced artificial intelligence architectures — which dictate how data is processed and used to produce reliable predictions or actions — to capture subtle, time-based pattern changes on the solar surface before an active region took shape. By analyzing data captured by the agency’s Solar Dynamics Observatory and using NASA Ames’ supercomputing resources, this new approach, published in the Journal of Geophysical Research: Machine Learning and Computation, looks at fluctuations in acoustic waves caused by sunspot regions when the regions form beneath the solar surface and begin the journey upward to emerge on the surface. 

“We cannot directly see the magnetic structure while it is still rising through the solar interior. Instead, we must look for indirect effects — very small changes in the magnetic field and in the pattern of acoustic waves continually traveling through the Sun,” said Alexander Kosovichev, a COFFIES co-investigator at NJIT. “The developed technique identifies precursors associated with an emerging active region in slight changes of the Sun’s acoustic power — more like a slight change in rhythm within a very noisy orchestra.” 

To develop current operational forecasts, the National Oceanic and Atmospheric Administration’s Space Weather Prediction Center and the United States Air Force monitor active regions that are already visible on the Sun to analyze the regions’ characteristics and estimate the probability of solar flares.

The COFFIES team aims to revolutionize this process. The AI model the team developed a specialized early detection system to handle very long sequences of data — called sliding-window transformer architecture — to use observations to find tiny reductions in the Sun’s acoustic activity and magnetic field, signals that scientists struggled to capture until now. These reductions form patterns that the AI model uses to predict active regions several hours before they become visible on the solar surface. Instead of looking at all activity on the solar surface at once, like earlier deep learning approaches have done, this new model moves a fixed-size “viewing window” across a long timeline of the Sun’s activity to focus on recent data while remembering overall patterns. This method allows forecasters the ability to predict approximate locations of emerging sunspots, rather than relying on counting already visible sunspots. 

This promising AI architecture shows how deep machine learning can contribute to heliophysics — the field studying the nature of the Sun and how it influences the very nature of space and the planets that exist there. While the model is not ready for operational real-time forecasting, the team plans to validate the approach across many more known solar events to fine-tune the model. 

NASA’s real-time space weather monitoring 

As NASA focuses on sending humans to explore the Moon with the Artemis missions and sending the first crewed missions to Mars, monitoring and forecasting space weather is important for ensuring the safety of our astronauts and the equipment they rely on. This predictive leap from the COFFIES team could prove vital for safeguarding technology and deep-space explorers from the volatile environment of our solar system.

Teams across NASA and NOAA collaborate to transition research capabilities into actual 360-degree space weather monitoring operational tools — including NASA’s Space Radiation Analysis Group, Moon to Mars Space Weather Analysis Office (M2M SWAO), and Community Coordinated Modeling Center as well as NOAA’s Space Weather Prediction Center. Sunspot region emergence prediction capabilities, especially of the Sun’s far side, could provide new information that supplements current models used by these teams.  

“The COFFIES AI model is exciting to our team because it could provide us with new capabilities towards predicting potential flaring locations ahead of time,” said Michelangelo Romano, M2M SWAO deputy director. “With this heads up, we can provide additional support to NASA missions.”

NASA’s COFFIES is one of three DRIVE Science Centers created to encourage collaborative science by establishing centers that are made of multidisciplinary teams from several institutions across the U.S. These pioneering facilities employ modelers, theoreticians, computer scientists, and observers to study important mysteries of our star and its influence, a branch of science known as heliophysics.  

The COFFIES team focuses on the interconnected processes behind the Sun’s activity. Understanding the Sun’s interior and magnetic variability is key to advancing our understanding of the Sun’s 11-year activity cycle and fine-tuning space weather forecasting tools.