IBM and NASA Release Open-Source AI Model to Support Lunar Exploration

IBM and NASA open-sourced a lunar AI model and unified dataset that outperform a leading baseline on several key Moon-mapping tasks.

Rhea-AI Summary

IBM (IBM) and NASA released the open-source NASA‑IBM Lunar Foundation Model on September 10, 2026 to support lunar exploration and research.

The AI model is trained on decades of multi-instrument lunar observations and aims to help identify potential ice deposits, volcanic formations and craters. Technical results cited show up to 22% lower error in predicting high-potential ice areas and up to 19% better crater detection at context scale versus the SwinV2-B baseline, with comparable or better accuracy and lower fine-tuning cost. IBM and NASA also released a unified, open lunar dataset aggregating over 30 spatially aligned layers from nine instruments across four missions.

Market Context

Before publication, IBM's prior-close series showed a 3.38% gain, while the momentum scanner listed ...

Analysis

Before publication, IBM's prior-close series showed a 3.38% gain, while the momentum scanner listed no peers, leaving no supplied evidence of a synchronized sector move alongside the lunar-model release.

Key Figures

Geographic feature identification improvement: up to 23% Lunar ice identification error reduction: up to 22% Volcanic feature accuracy improvement: 3% +3 more

Geographic feature identification improvement

up to 23%

Compared with widely used methods for lunar surface features

Lunar ice identification error reduction

up to 22%

RMSE reduction versus SwinV2-B (ImageNet)

Volcanic feature accuracy improvement

3%

Compared with SwinV2-B using imperfect labels

Crater detection improvement

nearly 19%

At approximately 100-meter context-scale resolution versus SwinV2-B

Dataset layers

over 30 spatially-aligned layers

Open-source lunar dataset aggregated from nine instruments across four missions

Dataset images and maps

tens of thousands

Images and maps of the lunar surface and subsurface

Key Terms

foundation model, rmse, multimodal, fine-tuning

4 terms

foundation model technical

"NASA-IBM Lunar Foundation Model, one of the first publicly available foundation models"

A foundation model is a large artificial intelligence system trained on vast, diverse data so it can be adapted to many tasks—like a universal engine that can be tuned to drive different products or services. Investors care because these models can lower the cost and time to build new AI-enabled offerings, create competitive advantages or concentration risks, and drive capital needs for compute, talent and regulation that affect company value.

rmse technical

"reduced error (RMSE) in identifying areas with high potential for lunar ice"

Root mean square error (RMSE) is a statistical measure that shows the typical size of the differences between predicted values and the actual outcomes, calculated as the square root of the average of the squared errors. For investors, RMSE gives a single-number sense of how far a model or forecast usually misses reality—think of it as the average distance of the misses measured in the same units as the data—so it’s useful for comparing models and judging forecast reliability.

multimodal technical

"The NASA-IBM model combines multimodal and multi-resolution observations"

Multimodal describes an approach, product, or system that uses two or more different types of inputs, methods, or channels — for example combining text, images and audio in a technology product, or blending drugs, devices and therapy in medical care. For investors, multimodal solutions can broaden market reach and competitive differentiation but also add development cost, operational complexity and regulatory hurdles; think of it like a hybrid car that offers more capabilities but requires more parts and oversight.

fine-tuning technical

"greater efficiency and lower fine-tuning costs"

Fine-tuning means making small, deliberate adjustments to a company’s tools, models, processes or plans to improve performance or accuracy without overhauling the whole system. Like tightening the strings on a guitar for a clearer note, these tweaks can reduce risk, cut costs, boost efficiency or sharpen forecasts, so investors watch fine‑tuning as a signal management is optimizing resources and responding to market or regulatory changes.

AI-generated analysis. How Rhea-AI works. Not financial advice.

See more from StockTitan in Google Search and AI answers. Adds StockTitan as a preferred source · opens Google

Add on Google Not now

• The NASA‑IBM Lunar Foundation Model turns decades of lunar observations into a foundation for discovery, helping scientists surface patterns across data at a scale no single instrument has provided
• The model exceeds widely used methods by up to 23% in identifying key geographic features on the Moon's surface, including potential ice deposits, craters and volcanic formations, to support a sustained return to the Moon

YORKTOWN HEIGHTS, N.Y., Sept. 10, 2026 /PRNewswire/ -- IBM (NYSE: IBM) and NASA today announced the open-source release of the NASA‑IBM Lunar Foundation Model, one of the first publicly available foundation models for scientific exploration of the Moon, now available. Trained on an extensive lunar observation dataset curated by IBM and NASA researchers, the model can help scientists turn decades of complex, multi-instrument data into insights to support the establishment of a sustained human presence on the Moon.

The Moon's topography is ever-changing. Over time, the Moon's surface has formed craters, distributed ice and even experienced volcanic activity. For decades, sensors and instruments have continuously observed the Moon, generating petabytes of data, but to study the Moon's surface, scientists need to either sift through maps and images by hand or use low resolution, task specific machine learning models. These methods can be computationally intensive and can lack the degree of scientific accuracy needed to identify and analyze geographic features. The newly released NASA-IBM Lunar Foundation Model will help researchers accelerate scientific progress by identifying hidden relationships between many different types and resolutions of lunar data.

Researchers could use the NASA-IBM Lunar Foundation Model to investigate multiple lunar phenomena, including:

• Potential Lunar Ice Deposits: Permanently shadowed regions are among the Moon's most difficult environments to observe, yet they may contain lunar ice below the surface. Lunar ice indicates the presence of water and oxygen — resources considered essential for a future Moon base and producing rocket fuel for future missions to Mars. The NASA-IBM model combines multimodal and multi-resolution observations to predict where ice may be present on the lunar surface. A NASA-IBM authored technical paper shows that the NASA-IBM model reduced error (RMSE) in identifying areas with high potential for lunar ice up to 22% compared to the SwinV2-B (ImageNet) model.¹
• Volcanic History: Scientists study lunar volcanic features, called Irregular Mare Patches, to better understand the Moon's volcanic history and thermal evolution. In addition, identifying these changing regions is strategic for future surface operations. Using imperfect labels, the model better captures the extent of the volcanic features than the SwinV2-B (ImageNet model by 3%, bringing comparable accuracy with greater efficiency and lower fine-tuning costs.²
• Crater Detection: Craters are one of the most important and distinguishing features of the Moon and can reveal important clues about its history, such as the age of different terrains, their geology, and the chemical composition of the early lunar interior. Crater mapping also helps NASA select safe landing sites, avoid hazards such as steep slopes and boulders, and plan locations for long-term lunar infrastructure. With the model, researchers can now identify, contextualize, and classify craters at meter-scale resolution with the cited paper showing comparable accuracy as state-of-the-art models like SwinV2-B while offering greater efficiency and lower fine-tuning costs. At context-scale resolution (~100 meters), it outperforms SwinV2-B by nearly 19% using just half the training data.³

"NASA has spent decades building an extraordinary scientific record of the Moon, but collecting data is only part of the job," said Kevin Murphy, chief science data officer and acting chief data and AI officer at NASA Headquarters in Washington. "We also have to make data easier for scientists to explore and use. The NASA-IBM Lunar Foundation Model shows what's possible when we bring AI to NASA's petabytes of scientific data. That's a real opportunity we see with AI: turning large-scale data into new discoveries."

"Uncovering the mysteries of the Moon requires an ability to learn from an extraordinary volume of scientific data," said Juan Bernabe-Moreno, Director of IBM Research Europe, UK and Ireland. "The NASA-IBM Lunar Foundation Model gives scientists a foundation to explore the Moon at scale, connecting observations across instruments, revealing patterns that are difficult to see in isolation, and providing an open platform the global research community can build on."

Despite the wealth of lunar data, no publicly available, unified dataset exists that brings the multi-modal, multi-resolution data into a common framework suitable for modern machine learning. Alongside the model, IBM and NASA scientists built the first open-source lunar dataset of its kind, a unified, machine learning ready lunar dataset aggregating over 30 spatially-aligned layers from nine instruments across four missions. The dataset combines tens of thousands of images and maps showing unique geophysical properties of the lunar surface from NASA's Lunar Reconnaissance Orbiter (LRO) and NASA's GRAIL mission and incorporated complementary lunar data from the Japanese Aerospace Exploration Agency's SELENE/Kaguya for a rich, multi-modal view of the lunar surface and subsurface available for the lunar science community to build on.

The model extends an established IBM and NASA collaboration that transforms valuable scientific data into an openly available foundation for discovery for the entire scientific community. By open sourcing the model, scientists and researchers have access to cutting edge AI systems to accelerate progress in lunar exploration. It joins the Prithvi family of open foundation models, spanning geospatial, weather, heliophysics and now the Moon. Together, these models advance a broader vision: instead of building a new algorithmic system for every scientific question, researchers can start from a shared model and adapt it to new tasks to accelerate discovery across domains.

About IBM
IBM is a leading provider of global hybrid cloud and AI, and consulting expertise. We help clients in more than 175 countries capitalize on insights from their data, streamline business processes, reduce costs and gain the competitive edge in their industries. Thousands of government and corporate entities in critical infrastructure areas such as financial services, telecommunications and healthcare rely on IBM's hybrid cloud platform and Red Hat OpenShift to affect their digital transformations quickly, efficiently and securely. IBM's breakthrough innovations in AI, quantum computing, industry-specific cloud solutions and consulting delivers open and flexible options to our clients. All of this is backed by IBM's long-standing commitment to trust, transparency, responsibility, inclusivity and service.

Media Contacts:

Ashley Peterson
IBM Research Communications
Ashley.peterson@ibm.com 

Maury Chasteau-Simien
IBM Research Communications
Maury@ibm.com 

¹ "Multimodal-Multiresolution Foundation Model for Lunar Remote Sensing", pg 17 (authored by IBM & NASA)
² "Multimodal-Multiresolution Foundation Model for Lunar Remote Sensing", pg 17 (authored by IBM & NASA)
³ "Multimodal-Multiresolution Foundation Model for Lunar Remote Sensing", pg 15 (authored by IBM & NASA)

View original content to download multimedia:https://www.prnewswire.com/news-releases/ibm-and-nasa-release-open-source-ai-model-to-support-lunar-exploration-302874829.html

SOURCE IBM

FAQ

What kinds of lunar phenomena can the NASA‑IBM Lunar Foundation Model help researchers study?

The model can be used to investigate potential lunar ice deposits in permanently shadowed regions, identify and delineate volcanic features known as Irregular Mare Patches, and detect, contextualize and classify craters at both meter-scale and context (~100 meter) resolution.

How does the model's performance compare to the SwinV2-B (ImageNet) baseline?

For high-potential lunar ice areas, the model reduced RMSE error by up to 22% compared with SwinV2-B. For volcanic feature mapping it improved extent capture by about 3% with greater efficiency and lower fine-tuning costs. At context-scale crater detection (~100 meters), it outperformed SwinV2-B by nearly 19% using only half the training data, while offering comparable accuracy at meter-scale resolution.

What data sources are included in the new unified lunar dataset?

The open-source dataset aggregates over 30 spatially aligned layers from nine instruments across four missions. It combines tens of thousands of images and maps from NASA's Lunar Reconnaissance Orbiter and GRAIL missions, along with complementary lunar data from JAXA's SELENE/Kaguya, to provide a multi-modal view of the lunar surface and subsurface.

How does this project relate to IBM's broader family of scientific AI models?

The NASA‑IBM Lunar Foundation Model joins IBM's Prithvi family of open foundation models, which spans geospatial, weather and heliophysics domains. The company said the shared goal is to let researchers start from common, openly available models and adapt them to specific scientific tasks rather than building new algorithms from scratch for every question.