{"id":12665,"date":"2026-08-14T17:00:23","date_gmt":"2026-08-14T17:00:23","guid":{"rendered":"https:\/\/rdgundem.com\/nasas-coffies-uses-ai-to-predict-storm-causing-active-regions-on-sun\/"},"modified":"2026-08-14T17:00:23","modified_gmt":"2026-08-14T17:00:23","slug":"nasas-coffies-uses-ai-to-predict-storm-causing-active-regions-on-sun","status":"publish","type":"post","link":"https:\/\/rdgundem.com\/en\/nasas-coffies-uses-ai-to-predict-storm-causing-active-regions-on-sun\/","title":{"rendered":"NASA\u2019s COFFIES Uses AI to Predict Storm-Causing Active Regions on Sun\u00a0"},"content":{"rendered":"
\n
\n
\n

5 min read<\/p>\n

NASA\u2019s COFFIES Uses AI to Predict Storm-Causing Active Regions on Sun\u00a0<\/h1>\n<\/div>\n<\/div>\n<\/div>\n

As humanity looks to the Moon and stars for future exploration, predicting space weather \u2014 conditions in space primarily driven by the Sun \u2014 is more important than ever.\u00a0<\/p>\n

Now, a team of astrophysicists and data scientists with NASA\u2019s\u00a0COFFIES<\/a> (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\u00a0Sun up\u00a0to 12 hours before they appear.\u00a0<\/p>\n

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.\u00a0<\/p>\n

\n
\n
\n
\"The<\/a><\/figure>
\n
NASA\u2019s Solar Dynamics Observatory captured this image of a solar flare \u2014 seen as the bright flash in the upper right \u2014 on June 30, 2026. The image shows a subset of extreme ultraviolet light that highlights the extremely hot material in flares and which is colorized in teal.<\/div>\n
NASA\u2019s Goddard Space Flight Center\/SDO<\/em>\u00a0<\/div>\n<\/figcaption><\/div>\n<\/div>\n<\/div>\n

By bridging\u00a0expertise\u00a0across different scientific institutions, COFFIES, a NASA\u00a0DRIVE<\/a>\u00a0(Diversify, Realize, Integrate, Venture, Educate) Science Center, brought together a team of researchers from New Jersey Institute of Technology (NJIT), Princeton University, and NASA\u2019s Ames Research Center<\/a> in California\u2019s Silicon Valley. The team turned to advanced artificial intelligence architectures \u2014 which dictate how data is processed and used to produce reliable predictions or actions \u2014 to capture subtle, time-based pattern changes on the solar surface before an active region took shape. By analyzing data captured by the agency\u2019s\u00a0Solar Dynamics Observatory<\/a>\u00a0and using NASA Ames\u2019\u00a0supercomputing resources<\/a>, this new approach,\u00a0published<\/a>\u00a0in 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.\u00a0<\/p>\n

\u201cWe cannot directly see the magnetic structure while it is still rising through the solar interior. Instead, we must look for indirect effects \u2014\u00a0very small\u00a0changes in the magnetic field and in the pattern of acoustic waves continually traveling through the Sun,\u201d said Alexander Kosovichev, a\u00a0COFFIES co-investigator at NJIT. \u201cThe developed technique identifies precursors associated with an emerging active region in slight changes of the Sun\u2019s acoustic power \u2014 more like a slight change in rhythm within a very noisy orchestra.\u201d\u00a0<\/p>\n

\n
\n

To view this video please enable JavaScript, and consider upgrading to a web browser that
\n\t\t\t\t\tsupports HTML5 video<\/a><\/p>\n

<\/video><\/div>\n<\/div>\n

\n
\n
This video is an example of what scientists use when analyzing the solar surface. This particular time frame tracks the magnetic field on the Sun\u2019s surface during the emergence of active region AR11158 in February 2011. The blue square grid highlights a target area on the Sun. The squares on the right side translates the data from the target grid area to show opposing magnetic polarities, indicated by the warm and cool-colored tones. The first column of blocks shows targeted areas at original resolution, the middle column displays data as 2D maps, and the right column plots changes in magnetic polarity over time as 1D curves. By watching these blocks, scientists can see signs of active region emergence, such as drops in acoustic waves and rises in magnetic fields. <\/div>\n<\/div>\n
\n
NASA\u2019s COFFIES DRIVE Science Center\/Irina Kitiashvili and Spiridon Kasapis<\/em><\/div>\n<\/div>\n<\/div>\n<\/div>\n

To develop current operational forecasts, the National Oceanic and Atmospheric Administration\u2019s Space Weather Prediction Center and the United States Air Force\u00a0monitor\u00a0active regions that are already visible on the Sun to analyze the regions\u2019 characteristics and estimate the probability of solar flares.<\/p>\n

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 \u2014 called sliding-window transformer architecture \u2014 to use observations to find tiny reductions in the Sun\u2019s 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 \u201cviewing window\u201d across a long timeline of the Sun\u2019s 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.\u00a0<\/p>\n

This promising AI architecture shows how deep machine learning can contribute to\u00a0heliophysics<\/a>\u00a0\u2014 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\u00a0validate\u00a0the approach across many more known solar events to fine-tune the model.\u00a0<\/p>\n

NASA\u2019s real-time space weather monitoring<\/strong>\u00a0<\/p>\n

As NASA focuses on sending humans to explore the Moon with the\u00a0Artemis<\/a>\u00a0missions and sending the first crewed missions to Mars,\u00a0monitoring\u00a0and 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.<\/p>\n

\n
\n

To view this video please enable JavaScript, and consider upgrading to a web browser that
\n\t\t\t\t\tsupports HTML5 video<\/a><\/p>\n

<\/video><\/div>\n<\/div>\n

\n
\n
NASA\u2019s Moon to Mars Space Weather Analysis Office monitors space weather 7 days a week. This important work helps decision makers not only protect people and equipment but maintain the services our modern society relies on every day. NASA\u2019s space weather monitoring is also critical for safeguarding astronauts as they journey to the Moon and onward to Mars. <\/div>\n<\/div>\n
\n
NASA\/Lacey Young<\/em><\/div>\n<\/div>\n<\/div>\n<\/div>\n

Teams across NASA and NOAA collaborate to transition research capabilities into actual 360-degree space weather\u00a0monitoring\u00a0operational tools \u2014 including NASA\u2019s Space Radiation Analysis Group, Moon to Mars Space Weather Analysis Office (M2M SWAO), and Community\u00a0Coordinated Modeling Center as well as NOAA\u2019s Space Weather Prediction Center. Sunspot region emergence prediction capabilities, especially of the Sun\u2019s far side, could provide\u00a0new information\u00a0that supplements current models used by these teams.\u00a0\u00a0<\/p>\n

\u201cThe COFFIES AI model is exciting to our team because it could provide us with new capabilities towards predicting potential flaring locations ahead of time,\u201d said Michelangelo Romano, M2M SWAO deputy director. \u201cWith\u00a0this heads\u00a0up, we can provide additional support to NASA missions.\u201d<\/p>\n

NASA\u2019s COFFIES is one of three DRIVE Science Centers\u00a0created to encourage collaborative science by\u00a0establishing\u00a0centers that are made of multidisciplinary teams from several institutions across the U.S.\u00a0These 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.\u00a0\u00a0<\/p>\n

The COFFIES team focuses on the interconnected processes behind the Sun\u2019s activity. Understanding the Sun\u2019s interior and magnetic variability is key to advancing our understanding of the Sun\u2019s 11-year activity cycle and fine-tuning space weather forecasting tools.\u00a0\u00a0<\/p>\n

\n
\n
\n

About the Author<\/h3>\n<\/div>\n<\/div>\n
\n
\n
\n
\"Desiree<\/div>\n
\n
\n

Desiree Apodaca<\/h2>\n<\/div>\n
NASA\u2019s Heliophysics Missions Communications Lead<\/div>\n
<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n

\n<\/div>\n<\/div>\n<\/div>\n

\n
\n
\n
\n
\n
\n

Share<\/h2>\n<\/div>\n
\n