Jump to content

Recommended Posts

  • Publishers
Posted

6 min read

NASA, IBM’s ‘Hot’ New AI Model Unlocks Secrets of Sun

GSFC_20171208_Archive_e001435~large.jpg?
This image from June 20, 2013 shows the bright light of a solar flare and an eruption of solar material shooting through the sun’s atmosphere, called a prominence eruption. Shortly thereafter, this same region of the sun sent a coronal mass ejection out into space — a phenomenon which can cause magnetic storms that degrade communication signals and cause unexpected electrical surges in power grids on Earth. NASA’s new heliophysics AI foundation model, Surya, can help predict these storms.
NASA/Goddard/SDO

NASA is turning up the heat in solar science with the launch of the Surya Heliophysics Foundational Model, an artificial intelligence (AI) model trained on 14 years of observations from NASA’s Solar Dynamics Observatory

Developed by NASA in partnership with IBM and others, Surya uses advances in AI to analyze vast amounts of solar data, helping scientists better understand solar eruptions and predict space weather that threatens satellites, power grids, and communication systems. The model can be used to provide early warnings to satellite operators and helps scientists predict how the Sun’s ultraviolet output affects Earth’s upper atmosphere.

Preliminary results show Surya is making strides in solar flare forecasting, a long-standing challenge in heliophysics. Surya, with its ability to generate visual predictions of solar flares two hours into the future, marks a major step towards the use of AI for operational space weather prediction. These initial results surpass existing benchmarks by 15%. By providing open access to the model on HuggingFace and the code on GitHub, NASA encourages the science and applications community to test and explore this AI model for innovative solutions that leverage the unique value of continuous, stable, long-duration datasets from the Solar Dynamics Observatory.

Illustrations of Solar Dynamics Observatory solar imagery used for training Surya: Solar coronal ultraviolet and extreme ultraviolet images from the Atmospheric Imaging Assembly (AIA) and solar surface velocity and magnetic field maps from the Helioseismic and Magnetic Imager (HMI).
Illustrations of Solar Dynamics Observatory solar imagery used for training Surya: Solar coronal ultraviolet and extreme ultraviolet images from the Atmospheric Imaging Assembly (AIA) and solar surface velocity and magnetic field maps from the Helioseismic and Magnetic Imager (HMI).
NASA/SDO

The model’s success builds directly on the Solar Dynamics Observatory’s long-term database. Launched in 2010, NASA’s Solar Dynamics Observatory has provided an unbroken, high-resolution record of the Sun for nearly 15 years through capturing images every 12 seconds in multiple wavelengths, plus precise magnetic field measurements. This stable, well-calibrated dataset, spanning an entire solar cycle, is uniquely suited for training AI models like Surya, enabling them to detect subtle patterns in solar behavior that shorter datasets would miss.

Surya’s strength lies in its foundation model architecture, which learns directly from raw solar data. Unlike traditional AI systems that require extensive labeling, Surya can adapt quickly to new tasks and applications. Applications include tracking active regions, forecasting flare activity, predicting solar wind speed, and integrating data from other observatories including the joint NASA-ESA Solar and Heliospheric Observatory mission and NASA’s Parker Solar Probe.

“We are advancing data-driven science by embedding NASA’s deep scientific expertise into cutting-edge AI models,” said Kevin Murphy, chief science data officer at NASA Headquarters in Washington. “By developing a foundation model trained on NASA’s heliophysics data, we’re making it easier to analyze the complexities of the Sun’s behavior with unprecedented speed and precision. This model empowers broader understanding of how solar activity impacts critical systems and technologies that we all rely on here on Earth.”

Three images of the Sun — the model input from January 7, 2014 at 3:24pm, the Surya model’s forecast for what the Sun would look like three hours later at 6:24pm, and the true observation from 6:24pm. The model forecast and the true observation are almost identical.
These images compare the ground-truth data (right) with model output (center) for solar flares, which are the events behind most space weather. Surya’s prediction is very close to what happened in reality (right). These preliminary results suggest that Surya has learned enough solar physics to predict the structure and evolution of a solar flare by looking at its beginning phase.
NASA/SDO/ODSI IMPACT AI Team

Solar storms pose significant risks to our technology-dependent society. Powerful solar events energize Earth’s ionosphere, resulting in substantial GPS errors or complete signal loss to satellite communications. They also pose risks to power grids, as geomagnetically induced currents from coronal mass ejections can overload transformers and trigger widespread outages.

In commercial aviation, solar flares can disrupt radio communications and navigation systems while exposing high-altitude flights to increased radiation. The stakes are even higher for human spaceflight. Astronauts bound for the Moon or Mars may need to depend on precise predictions to shelter from intense radiation during solar particle events.

The Sun’s influence extends to the growing number of low Earth orbit satellites, including those that deliver global high-speed internet. As solar activity intensifies, it heats Earth’s upper atmosphere, increasing drag that slows satellites, pulls them from orbit, and causes premature reentry. Satellite operators often struggle to forecast where and when solar flares might affect these satellites.

A row of Solar Dynamic Observatory images followed by a row of predictions from the Surya model. The two rows are almost identical.
The “ground truth” solar activity is shown on the top row. The bottom row shows solar activity predicted by Surya.
NASA/SDO/ODSI IMPACT AI Team

“Our society is built on technologies that are highly susceptible to space weather,” said Joseph Westlake, Heliophysics Division director at NASA Headquarters. “Just as we use meteorology to forecast Earth’s weather, space weather forecasts predict the conditions and events in the space environment that can affect Earth and our technologies. Applying AI to data from our heliophysics missions is a vital step in increasing our space weather defense to protect astronauts and spacecraft, power grids and GPS, and many other systems that power our modern world.”

While Surya is designed to study the Sun, its architecture and methodology are adaptable across scientific domains. From planetary science to Earth observation, the project lays the foundational infrastructure for similar AI efforts in diverse domains.

Surya is part of a broader NASA push to develop open-access, AI-powered science tools. Both the model and training datasets are freely available online to researchers, educators, and students worldwide, lowering barriers to participation and sparking new discoveries.

A graphic showing the process of training the Surya heliophysics AI model. First, NASA’s Solar Dynamics Observatory collects observational data about the Sun. Then, that data is preprocessed for the model. Then, the model is pretrained, and finally, the heliophysics foundation model is ready for use.
The process for creating Surya. Foundation models enhance the utility of NASA’s Solar Dynamics Observatory datasets and create a base for building new applications.
NASA/ODSI IMPACT AI Team

Surya’s training was supported in part by the National Artificial Intelligence Research Resource (NAIRR) Pilot, a National Science Foundation (NSF)-led initiative that provides researchers with access to advanced computing, datasets, and AI tools. The NAIRR Pilot brings together federal and industry resources, such as computing power from NVIDIA, to expand access to the infrastructure needed for cutting-edge AI research.

“This project shows how the NAIRR Pilot is uniting federal and industry AI resources to accelerate scientific breakthroughs,” said Katie Antypas, director of NSF’s Office of Advanced Cyberinfrastructure. “With support from NVIDIA and NSF, we’re not only enabling today’s research, we’re laying the groundwork for a national AI network to drive tomorrow’s discoveries.”

Surya is part of a larger effort championed and supported by NASA’s Office of the Chief Science Data Officer and Heliophysics Division, the NSF , and partnering universities to advance NASA’s scientific missions through innovative data science and AI models. Surya’s AI architecture was jointly developed by the Interagency Implementation and Advanced Concepts Team (IMPACT) under the Office of Data Science and Informatics  at NASA’s Marshall Space Flight Center in Huntsville, Alabama; IBM; and a collaborative science team.

The science team, assembled by NASA Headquarters, consisted of experts from the Southwest Research Institute in San Antonio, Texas; the University of Alabama in Huntsville in Huntsville, Alabama; the University of Colorado Boulder in Boulder, Colorado; Georgia State University in Atlanta, Georgia; Princeton University in Princeton, New Jersey; NASA’s SMD’s Heliophysics Division; NASA’s Goddard Space Flight Center in Greenbelt, Maryland; NASA’s Jet Propulsion Laboratory in Pasadena, California; and the SETI Institute in Mountain View, California.

For a behind-the-scenes dive into Surya’s architecture, industry and academic collaborations, challenges behind developing the model, read the blog post on NASA’s Science Data Portal:

https://science.data.nasa.gov/features-events/inside-surya-solar-ai-model

For more information about NASA’s strategy of developing foundation models for science, visit:

https://science.nasa.gov/artificial-intelligence-science

View the full article

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

  • Similar Topics

    • By NASA
      NASA’s Northrop Grumman Commercial Resupply Services 23 Installation
    • By NASA
      6 min read
      Preparations for Next Moonwalk Simulations Underway (and Underwater)
      It’s been 30 years since the discovery of the first planet around another star like our Sun. With every new discovery, scientists move closer to answering whether there are other planets like Earth that could host life as we know it. NASA/JPL-Caltech The milestone highlights the accelerating rate of discoveries, just over three decades since the first exoplanets were found.
      The official number of exoplanets — planets outside our solar system — tracked by NASA has reached 6,000. Confirmed planets are added to the count on a rolling basis by scientists from around the world, so no single planet is considered the 6,000th entry. The number is monitored by NASA’s Exoplanet Science Institute (NExScI), based at Caltech’s IPAC in Pasadena, California. There are more than 8,000 additional candidate planets awaiting confirmation, with NASA leading the world in searching for life in the universe.
      See NASA's Exoplanet Discoveries Dashboard “This milestone represents decades of cosmic exploration driven by NASA space telescopes — exploration that has completely changed the way humanity views the night sky,” said Shawn Domagal-Goldman, acting director, Astrophysics Division, NASA Headquarters in Washington. “Step by step, from discovery to characterization, NASA missions have built the foundation to answering a fundamental question: Are we alone? Now, with our upcoming Nancy Grace Roman Space Telescope and Habitable Worlds Observatory, America will lead the next giant leap — studying worlds like our own around stars like our Sun. This is American ingenuity, and a promise of discovery that unites us all.”
      Scientists have found thousands of exoplanets (planets outside our solar system) throughout the galaxy. Most can be studied only indirectly, but scientists know they vary widely, as depicted in this artist’s concept, from small, rocky worlds and gas giants to water-rich planets and those as hot as stars. NASA’s Goddard Space Flight Center The milestone comes 30 years after the first exoplanet was discovered around a star similar to our Sun, in 1995. (Prior to that, a few planets had been identified around stars that had burned all their fuel and collapsed.) Although researchers think there are billions of planets in the Milky Way galaxy, finding them remains a challenge. In addition to discovering many individual planets with fascinating characteristics as the total number of known exoplanets climbs, scientists are able to see how the general planet population compares to the planets of our own solar system.
      For example, while our solar system hosts an equal number of rocky and giant planets, rocky planets appear to be more common in the universe. Researchers have also found a range of planets entirely different from those in our solar system. There are Jupiter-size planets that orbit closer to their parent star than Mercury orbits the Sun; planets that orbit two stars, no stars, and dead stars; planets covered in lava; some with the density of Styrofoam; and others with clouds made of gemstones.
      “Each of the different types of planets we discover gives us information about the conditions under which planets can form and, ultimately, how common planets like Earth might be, and where we should be looking for them,” said Dawn Gelino, head of NASA’s Exoplanet Exploration Program (ExEP), located at the agency’s Jet Propulsion Laboratory in Southern California. “If we want to find out if we’re alone in the universe, all of this knowledge is essential.” 
      Searching for other worlds
      Fewer than 100 exoplanets have been directly imaged, because most planets are so faint they get lost in the light from their parent star. The other four methods of planet detection are indirect. With the transit method, for instance, astronomers look for a star to dim for a short period as an orbiting planet passes in front of it.
      To account for the possibility that something other than an exoplanet is responsible for a particular signal, most exoplanet candidates must be confirmed by follow-up observations, often using an additional telescope, and that takes time. That’s why there is a long list of candidates in the NASA Exoplanet Archive (hosted by NExScI) waiting to be confirmed.
      “We really need the whole community working together if we want to maximize our investments in these missions that are churning out exoplanets candidates,” said Aurora Kesseli, the deputy science lead for the NASA Exoplanet Archive at IPAC. “A big part of what we do at NExScI is build tools that help the community go out and turn candidate planets into confirmed planets.”
      The rate of exoplanet discoveries has accelerated in recent years (the database reached 5,000 confirmed exoplanets just three years ago), and this trend seems likely to continue. Kesseli and her colleagues anticipate receiving thousands of additional exoplanet candidates from the ESA (European Space Agency) Gaia mission, which finds planets through a technique called astrometry, and NASA’s upcoming Nancy Grace Roman Space Telescope, which will discover thousands of new exoplanets primarily through a technique called gravitational microlensing.
      Many telescopes contribute to the search for and study of exoplanets, including some in space (artists concepts shown here) and on the ground. Doing the work are organizations around the world, including ESA (European Space Agency), CSA (Canadian Space Agency), and NSF (National Science Foundation). NASA/JPL-Caltech Future exoplanets
      At NASA, the future of exoplanet science will emphasize finding rocky planets similar to Earth and studying their atmospheres for biosignatures — any characteristic, element, molecule, substance, or feature that can be used as evidence of past or present life. NASA’s James Webb Space Telescope has already analyzed the chemistry of over 100 exoplanet atmospheres.
      But studying the atmospheres of planets the size and temperature of Earth will require new technology. Specifically, scientists need better tools to block the glare of the star a planet orbits. And in the case of an Earth-like planet, the glare would be significant: The Sun is about 10 billion times brighter than Earth — which would be more than enough to drown out our home planet’s light if viewed by a distant observer.
      NASA has two main initiatives to try overcoming this hurdle. The Roman telescope will carry a technology demonstration instrument called the Roman Coronagraph that will test new technologies for blocking starlight and making faint planets visible. At its peak performance, the coronagraph should be able to directly image a planet the size and temperature of Jupiter orbiting a star like our Sun, and at a similar distance from that star. With its microlensing survey and coronagraphic observations, Roman will reveal new details about the diversity of planetary systems, showing how common solar systems like our own may be across the galaxy.
      Additional advances in coronagraph technology will be needed to build a coronagraph that can detect a planet like Earth. NASA is working on a concept for such a mission, currently named the Habitable Worlds Observatory.
      More about ExEP, NExScI 
      NASA’s Exoplanet Exploration Program is responsible for implementing the agency’s plans for the discovery and understanding of planetary systems around nearby stars. It acts as a focal point for exoplanet science and technology and integrates cohesive strategies for future discoveries. The science operations and analysis center for ExEP is NExScI, based at IPAC, a science and data center for astrophysics and planetary science at Caltech. JPL is managed by Caltech for NASA.
      /
      News Media Contact
      Calla Cofield
      Jet Propulsion Laboratory, Pasadena, Calif.
      626-808-2469
      calla.e.cofield@jpl.nasa.gov
      2025-119
      Share
      Details
      Last Updated Sep 17, 2025 Related Terms
      Exoplanets Exoplanet Discoveries Gas Giant Exoplanets Jet Propulsion Laboratory Kepler / K2 Nancy Grace Roman Space Telescope Neptune-Like Exoplanets Super-Earth Exoplanets Terrestrial Exoplanets TESS (Transiting Exoplanet Survey Satellite) The Search for Life Explore More
      7 min read How NASA’s Roman Mission Will Unveil Our Home Galaxy Using Cosmic Dust
      Article 1 day ago 2 min read NASA Makes Webby 30s List of Most Iconic, Influential on Internet
      Article 1 day ago 4 min read NASA Analysis Shows Sun’s Activity Ramping Up
      Article 2 days ago Keep Exploring Discover Related Topics
      Missions
      Humans in Space
      Climate Change
      Solar System
      View the full article
    • By NASA
      NASA Prelaunch News Conference on Three New Space Weather Missions (Sept. 21, 2025)
    • By NASA
      NASA Science News Conference on Three New Space Weather Missions (Sept. 21, 2025)
    • By NASA
      6 min read
      NASA’s IMAP Mission to Study Boundaries of Our Home in Space
      Summary
      NASA’s new Interstellar Mapping and Acceleration Probe, or IMAP, will launch no earlier than Tuesday, Sept. 23 to study the heliosphere, a giant shield created by the Sun. The mission will chart the heliosphere’s boundaries to help us better understand the protection it offers life on Earth and how it changes with the Sun’s activity. The IMAP mission will also provide near real-time measurements of the solar wind, data that can be used to improve models predicting the impacts of space weather ranging from power-line disruptions to loss of satellites, to the health of voyaging astronauts. Space is a dangerous place — one that NASA continues to explore for the benefit of all. It’s filled with radiation and high-energy particles that can damage DNA and circuit boards alike. Yet life endures in our solar system in part because of the heliosphere, a giant bubble created by the Sun that extends far beyond Neptune’s orbit.
      With NASA’s new Interstellar Mapping and Acceleration Probe, or IMAP, launching no earlier than Tuesday, Sept. 23, humanity is set to get a better look at the heliosphere than ever before. The mission will chart the boundaries of the heliosphere to help us better understand the protection it offers and how it changes with the Sun’s activity. The IMAP mission will also provide near real-time measurements of space weather conditions essential for the Artemis campaign and deep space travel. 
      “With IMAP, we’ll push forward the boundaries of knowledge and understanding of our place not only in the solar system, but our place in the galaxy as a whole,” said Patrick Koehn, IMAP program scientist at NASA Headquarters in Washington. “As humanity expands and explores beyond Earth, missions like IMAP will add new pieces of the space weather puzzle that fills the space between Parker Solar Probe at the Sun and the Voyagers beyond the heliopause.”
      Download this video from NASA’s Scientific Visualization Studio.
      Domain of Sun
      The heliosphere is created by the constant outflow of material and magnetic fields from the Sun called the solar wind. As the solar system moves through the Milky Way, the solar wind’s interaction with interstellar material carves out the bubble of the heliosphere. Studying the heliosphere helps scientists understand our home in space and how it came to be habitable.
      As a modern-day celestial cartographer, IMAP will map the boundary of our heliosphere and study how the heliosphere interacts with the local galactic neighborhood beyond. It will chart the vast range of particles, dust, ultraviolet light, and magnetic fields in interplanetary space, to investigate the energization of charged particles from the Sun and their interaction with interstellar space.
      The IMAP mission builds on NASA’s Voyager and IBEX (Interstellar Boundary Explorer) missions. In 2012 and 2018, the twin Voyager spacecraft became the first human-made objects to cross the heliosphere’s boundary and send back measurements from interstellar space. It gave scientists a snapshot of what the boundary looked like and where it was in two specific locations. While IBEX has been mapping the heliosphere, it has left many questions unanswered. With 30 times higher resolution and faster imaging, IMAP will help fill in the unknowns about the heliosphere.
      Energetic neutral atoms: atomic messengers from our heliosphere’s edge
      Of IMAP’s 10 instruments, three will investigate the boundaries of the heliosphere by collecting energetic neutral atoms, or ENAs. Many ENAs originate as positively charged particles released by the Sun but after racing across the solar system, these particles run into particles in interstellar space. In this collision, some of those positively charged particles become neutral, and an energetic neutral atom is born. The interaction also redirects the new ENAs, and some ricochet back toward the Sun.
      Charged particles are forced to follow magnetic field lines, but ENAs travel in a straight line, unaffected by the twists, turns, and turbulences in the magnetic fields that permeate space and shape the boundary of the heliosphere. This means scientists can track where these atomic messengers came from and study distant regions of space from afar. The IMAP mission will use the ENAs it collects near Earth to trace back their origins and construct maps of the boundaries of the heliosphere, which would otherwise be invisible from such a distance.
      “With its comprehensive state-of-the-art suite of instruments, IMAP will advance our understanding of two fundamental questions of how particles are energized and transported throughout the heliosphere and how the heliosphere itself interacts with our galaxy,” said Shri Kanekal, IMAP mission scientist at NASA’s Goddard Space Flight Center in Greenbelt, Maryland.
      The IMAP mission will study the heliosphere, our home in space. NASA/Princeton University/Patrick McPike Space weather: monitoring solar wind
      The IMAP mission will also support near real-time observations of the solar wind and energetic solar particles, which can produce hazardous conditions in the space environment near Earth. From its location at Lagrange Point 1, about 1 million miles from Earth toward the Sun, IMAP will provide around a half hour’s warning of dangerous particles headed toward our planet. The mission’s data will help with the development of models that can predict the impacts of space weather ranging from power-line disruptions to loss of satellites.
      “The IMAP mission will provide very important information for deep space travel, where astronauts will be directly exposed to the dangers of the solar wind,” said David McComas, IMAP principal investigator at Princeton University.
      Cosmic dust: hints of the galaxy beyond
      In addition to measuring ENAs and solar wind particles, IMAP will also make direct measurements of interstellar dust — clumps of particles originating outside of the solar system that are smaller than a grain of sand. This space dust is largely composed of rocky or carbon-rich grains leftover from the aftermath of supernova explosions. 
      The specific elemental composition of this space dust is a postmark for where it comes from in the galaxy. Studying cosmic dust can provide insight into the compositions of stars from far outside our solar system. It will also help scientists significantly advance what we know about these basic cosmic building materials and provide information on what the material between stars is made of.
      David McComas leads the mission with an international team of 27 partner institutions. APL is managing the development phase and building the spacecraft, and it will operate the mission. IMAP is the fifth mission in NASA’s Solar Terrestrial Probes Program portfolio. The Explorers and Heliophysics Projects Division at NASA Goddard manages the STP Program for the agency’s Heliophysics Division of NASA’s Science Mission Directorate. NASA’s Launch Services Program, based at NASA’s Kennedy Space Center in Florida, manages the launch service for the mission.
      By Mara Johnson-Groh
      NASA’s Goddard Space Flight Center, Greenbelt, Md.
      Share








      Details
      Last Updated Sep 17, 2025 Related Terms
      Goddard Space Flight Center Heliophysics Heliophysics Division IMAP (Interstellar Mapping and Acceleration Probe) Missions NASA Centers & Facilities NASA Directorates Science & Research Science Mission Directorate Explore More
      4 min read NASA Interns Apply NASA data to Real-World Problems to Advance Space Research and Aerospace Innovation


      Article


      2 hours ago
      3 min read Regions on Asteroid Explored by NASA’s Lucy Mission Get Official Names
      The IAU (International Astronomical Union), a global naming authority for celestial objects, has approved official…


      Article


      1 day ago
      5 min read Connecting Educators with NASA Data: Learning Ecosystems Northeast in Action


      Article


      2 days ago
      Keep Exploring Discover More Topics From NASA
      Missions



      Humans in Space



      Climate Change



      Solar System


      View the full article
  • Check out these Videos

×
×
  • Create New...