Live Feeds
● LIVE Updated 25m ago · 19 sources tracked

IBM, NASA launch AI model to help map ice, craters on Moon

NASA and IBM have launched the Lunar Foundation Model, a free open-source AI tool designed to map volcanic sites, craters, and ice on the Moon. The model identifies water ice and analyzes data from five Moon-orbiting spacecraft, utilizing a training set of over two million images. This tool is hosted on Hugging Face with its codebase available on GitHub to help astronauts locate critical resources. While some reports indicate the AI improves water ice detection accuracy by 22%, other data suggests it outperforms existing mapping methods by 23%.

🎙️

Listen to Live Briefing

Real-time synthesized voice briefing · Live Feeds Desk

⏱ ~3 min
Speed:
RSS Source map (19)
Key Developments & Real-Time Context
Text size:
  • NASA and IBM released the open-source Lunar Foundation Model to map lunar ice, craters, and volcanic sites.
  • The AI model was trained on more than two million images from five Moon-orbiting spacecraft.
  • The tool is available for free via GitHub and Hugging Face.
🛡️ Source Corroboration: 19 independent reporting domains (90% confidence) ⏱ Read time: ~2 min

What changed

Updated training data reveals the AI used more than two million images from five different spacecraft.

Live updates

  1. NASA and IBM Release Open-Source Lunar Foundation Model for Moon Mapping

    NASA and IBM have launched the Lunar Foundation Model, a free open-source AI tool designed to map volcanic sites, craters, and ice on the Moon. The model identifies water ice and analyzes data from five Moon-orbiting spacecraft, utilizing a training set of over two million images. This tool is hosted on Hugging Face with its codebase available on GitHub to help astronauts locate critical resources. While some reports indicate the AI improves water ice detection accuracy by 22%, other data suggests it outperforms existing mapping methods by 23%.

    Why it matters

    Accurate mapping of lunar ice is essential for sustainable human presence on the Moon, as water provides life support and fuel. The model leverages 17 years of Lunar Reconnaissance Orbiter data. This release follows a 2% increase in IBM stock.

    What is confirmed

    • NASA and IBM released the open-source Lunar Foundation Model to map lunar ice, craters, and volcanic sites.
    • The AI model was trained on more than two million images from five Moon-orbiting spacecraft.
    • The tool is available for free via GitHub and Hugging Face.

    Still unconfirmed

    • The AI spots Moon water ice 22% more accurately.
    • The AI beats existing mapping methods by 23%.

    What to watch next

    • Verification of the specific accuracy percentage for water ice detection
    • Deployment of the model in active astronaut resource missions
    Sources used for this update (4)
    1. tech.yahoo.com — NASA-IBM Lunar Foundation Model puts free AI moon mapping in anyone’s hands
    2. www.martincid.com — NASA and IBM released a free AI that spots Moon water ice 22% more accurately
    3. www.marketscreener.com — IBM's Anderon Unit Finalizes $1 Billion CHIPS Award for US Quantum Foundry
    4. www.marketscreener.com — Anderon Finalizes Agreement With The U.S. Department Of Commerce For $1 Billion CHIPS Award To Accelerate R&D For U.S.-Based Pure-Play Quantum Foundry
    confidence 90%
  2. IBM shares rise as Lunar Foundation Model improves moon mapping

    IBM stock rose 2% following the release of the NASA-IBM Lunar Foundation Model, an open-source AI designed to map lunar ice, craters, and volcanic features. The model analyzes 17 years of data from the Lunar Reconnaissance Orbiter to identify subsurface ice in polar craters. While previous reports cited a 22% error reduction, newer data indicates the AI beats existing mapping methods by 23%. The codebase is available on GitHub and the model is hosted on Hugging Face to assist astronauts in locating critical resources.

    Why it matters

    Mapping water ice is essential for sustainable human presence on the Moon. This AI processes petabytes of information to find reserves in permanently shadowed regions. It represents a collaboration between NASA and IBM to modernize lunar exploration data.

    What is confirmed

    • NASA and IBM released the open-source Lunar Foundation Model to map ice, craters, and volcanic features.
    • The AI model is hosted on Hugging Face with its codebase on GitHub.
    • The system was trained on 17 years of data primarily from the Lunar Reconnaissance Orbiter.
    • The AI identifies subsurface ice reserves in permanently shadowed polar craters.

    Still unconfirmed

    • IBM stock gained 2% due to the Lunar AI beating mapping methods by 23%.

    What to watch next

    • Verification of the 23% performance increase against the previously reported 22% error reduction
    • Integration of the model into active astronaut mission planning
    • Further releases of open-source lunar data sets on Hugging Face
    Sources used for this update (4)
    1. mynews13.com — NASA and SpaceX successfully launch Nancy Grace Roman telescope
    2. finance.yahoo.com — IBM Gains 2% as Lunar AI Beats Mapping Methods by 23%
    3. Engadget — NASA And IBM Made An AI Model For Exploring The Moon
    4. www.techexplorist.com — NASA and IBM’s new AI could help astronauts find ice on the Moon
    confidence 90%
  3. NASA and IBM launch open-source AI model to map lunar surface

    NASA and IBM released the NASA-IBM Lunar Foundation Model on September 10, 2026, to help researchers map lunar ice, craters, and volcanic features. The open-source model is hosted on Hugging Face with its codebase available on GitHub. Trained on 17 years of data primarily from the Lunar Reconnaissance Orbiter, the AI analyzes petabytes of information to identify subsurface ice reserves in permanently shadowed polar craters. The system predicts ice locations with 22% less error than the best existing dedicated models.

    Why it matters

    NASA intends to return humans to the Moon in 2028. Mapping water ice is critical for sustaining future lunar missions and human survival. This tool allows academic institutions and the public to analyze lunar geology using standardized AI.

    What is confirmed

    • The NASA-IBM Lunar Foundation Model was released on September 10, 2026.
    • The AI model is open-source and hosted on Hugging Face with code on GitHub.
    • The model maps lunar ice, craters, and volcanic features.
    • The AI was trained primarily on 17 years of data from NASA's Lunar Reconnaissance Orbiter.
    • NASA aims to return humans to the Moon in 2028.

    Still unconfirmed

    • The model predicts where Moon ice may be buried with 22% less error than the best available dedicated models.
    • The model analyzes petabytes of moon data.

    What to watch next

    • Verification of ice location accuracy by independent researchers using the open-source code
    • Integration of the model into mission planning for the 2028 human lunar return
    Sources used for this update (12)
    1. Reuters — IBM, NASA launch AI model to help map ice, craters on Moon
    2. NASA Science (.gov) — NASA, IBM Launch AI Foundation Model for Lunar Science
    3. IBM Research — Introducing IBM and NASA’s new foundation model for the Moon
    4. fastcompany.com — NASA wants humans back on the Moon in 2028. IBM’s new AI could help get them there
    5. CNET — NASA and IBM Launch Open-Source AI Model for Future Moon Explorations
    6. americanbazaaronline.com — IBM, NASA launch AI model to map Moon’s ice, craters
    7. www.techrepublic.com — NASA and IBM Launch Open AI Model for Lunar Research
    8. www.itnews.com.au — IBM, NASA launch AI model
    9. www.techtimes.com — NASA and IBM Open-Source Lunar AI That Pinpoints Moon Ice 22% More Accurately
    10. Phys.org — Release of open AI model trained on 17 years of lunar data maps ice, craters and volcanoes
    11. www.tomorrowsworldtoday.com — NASA and IBM Built an AI to Find Ice on the Moon
    12. hothardware.com — NASA & IBM Built An AI To Find Moon Water So We Don't Die Of Thirst Up There
    confidence 95%
📊

Community Sentiment: How do you assess this situation?

Voice your perspective · Real-time aggregated sentiment from the Live Feeds community