OFICIAL NASA News Releases

NASA’s COFFIES Uses AI to Predict Storm-Causing Active Regions

What happened
Based on NASA News Releases · Aug 14, 2026

NASA’s COFFIES team developed an AI model using machine learning to predict solar active regions up to 12 hours before they emerge, potentially improving space weather forecasting for astronaut and satellite safety.

🚩 Report a correction ↗ Open source

Video

Video available

Key points
·
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.
·
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.
Key numbers
·
NASA’s COFFIES (Consequence Of Fields and Flows in the Interior and Exterior of the Sun) team, including researchers from NJIT, Princeton University, and NASA’s Ames Research Center, has created a machine-learning model to forecast the...
·
NASA’s COFFIES team developed an AI model using machine learning to predict solar active regions up to 12 hours before they emerge, potentially improving space weather forecasting for astronaut and satellite safety.
·
A team with NASA’s COFFIES 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.

NASA’s COFFIES (Consequence Of Fields and Flows in the Interior and Exterior of the Sun) team, including researchers from NJIT, Princeton University, and NASA’s Ames Research Center, has created a machine-learning model to forecast the appearance of active regions on the Sun up to 12 hours in advance. These regions, marked by sunspots, drive severe space weather events such as solar flares and coronal mass ejections, which can disrupt communications and threaten astronauts and satellites.

The model analyzes subtle changes in acoustic waves and magnetic fields detected by NASA’s Solar Dynamics Observatory, using a sliding-window transformer architecture to identify precursors to emerging active regions. Unlike earlier deep learning approaches, this method focuses on recent data while retaining long-term patterns, enabling predictions of sunspot locations before they become visible on the solar surface.

Current operational forecasts rely on monitoring already visible active regions, but COFFIES aims to transform this process. The AI system detects tiny reductions in acoustic power and magnetic activity, signals previously difficult to capture, to predict active regions hours before emergence. While not yet ready for real-time use, the team plans further validation to refine the model for future applications.

The breakthrough could enhance space weather monitoring critical for NASA’s Artemis and Mars missions. Teams at NASA and NOAA, including the Moon to Mars Space Weather Analysis Office, are collaborating to integrate such research into operational tools. Michelangelo Romano, M2M SWAO deputy director, noted the model’s potential to predict flaring locations ahead of time, providing early support for NASA missions.

Original source → Deals on Clipraptor.com →