NASA is bringing artificial intelligence to the study of the Moon, helping researchers transform how they analyze the Moon’s surface. In an ongoing collaboration with IBM Research and several academic institutions, NASA has launched the NASA-IBM Lunar Foundation Model, among the first open-source AI models built specifically for lunar science. The model, trained primarily on data from NASA’s Lunar Reconnaissance Orbiter (LRO), is hosted publicly on Hugging Face for anyone to use, with the complete codebase available on GitHub for testing and experimentation.

The NASA-IBM Lunar Foundation Model supports the next generation of lunar science by helping researchers quickly analyze vast quantities of data to better understand the Moon’s surface. Using the model as a mapping tool, researchers can rapidly develop actionable strategies for evaluating the Moon’s rugged surface, understanding its geological past, and planning future lunar research.

“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.”

Unlike traditional models that require building and training specialized algorithms from scratch for specific tasks, foundation models are pre-trained on vast, unlabeled datasets. The broad knowledge they acquire through pre-training allows them to generalize across multiple scientific domains through quick fine-tuning, making foundation models both versatile and efficient in accelerating scientific research.

Data collected by NASA’s LRO over the past 17 years was well-suited for training this foundation model because it covers most of the lunar surface in detail. The data produced from the LRO mission is larger than all other NASA planetary missions combined, capturing an almost seamless, high-resolution mosaic of the entire Moon. The NASA-IBM model was trained on roughly 2 million image tiles from this dataset, comprising more than 1 million high-resolution camera images at 1-meter resolution and nearly 964,000 multispectral images at 100-meter resolution. The model also was trained on high-resolution Moon imagery and terrain data from multiple other missions such as NASA’s GRAIL (Gravity Recovery and Interior Laboratory), NASA’s Lunar Prospector, and JAXA’s (Japan Aerospace Exploration Agency) Selenological and Engineering Explorer.

Because the foundation model is already pre-trained on this dataset, planetary scientists can adapt the model to many different lunar research tasks such as mapping craters, spotting young volcanic features, and estimating where ice may exist near the lunar poles by using only small amounts of labeled data. For researchers who study the Moon’s polar ice, the NASA-IBM model can help them estimate where ice patches are likely to be stable, on and below the surface. Dark areas like the Moon’s permanently shadowed regions remain cold enough to trap and preserve ice for up to billions of years. Studying these areas offers insight into the Moon’s history and presents an opportunity to map potentially usable resources for future space exploration.

While the Moon is thought to no longer be volcanically active, it once experienced dynamic geological processes. For researchers studying lunar volcanism, the NASA-IBM model accelerates the identification of unusual looking volcanic features known as irregular mare patches. Because these structures appear relatively young, they challenge established timelines for lunar cooling, and mapping them could help scientists piece together a more accurate understanding of the Moon’s thermal evolution.

The model also can map surface features, such as craters, more efficiently than manual methods. Every crater is formed by an impact, making crater counts and measurements essential for dating the lunar surface and reconstructing solar system history. The foundation model helps speed up the process of identifying and measuring craters, allowing scientists to focus on interpreting findings and determining their implications for exploration.

Overall, the model matched or exceeded the performance of several other strong baseline models across all evaluated tasks, achieving comparable results on crater mapping and segmentation of irregular mare patches, while demonstrating a clear advantage on estimating polar ice stability.

The NASA-IBM Lunar Foundation Model is part of the agency’s Office of the Chief Science Data Officer’s strategy for AI for science — a larger, ongoing collaboration between NASA and IBM aimed at using advanced AI to explore our planet and solar system. It joins a growing collection of AI models developed through this partnership, including:

• The Prithvi Models: a family of models pre-trained on Earth observation data and designed to support applications such as disaster monitoring, flood mapping, crop yield prediction, and hurricane prediction.
• The Surya Model: a heliophysics model trained on high-resolution solar observation data to predict space weather phenomena such as solar flares which can disrupt power grids and satellite operations.

Within NASA, the Impact AI team at the agency’s Marshall Space Flight Center in Huntsville, Alabama, collaborated with scientists in the agency’s Science Mission Directorate Planetary Science Division, NASA’s Goddard Space Flight Center in Greenbelt, Maryland, and NASA’s Ames Research Center in California’s Silicon Valley, to build the NASA-IBM model. The model is an example of open science in action, uniting experts from NASA, industry, and academia to turn raw data into a resource for lunar discovery. To support the global research community, the team released comprehensive machine learning-ready pre-training datasets and benchmark collections alongside the model, which is integrated into the open-source TerraTorch toolkit. Supported by a companion paper available on Hugging Face, this open release ensures reproducible research and equips scientists worldwide to build, compare, and refine AI models for the future of lunar exploration.

The science team, assembled by NASA Headquarters, included experts from the Universities Space Research Association in Huntsville, Alabama; the SETI Institute in Silicon Valley, California; the University of Maryland, Baltimore County in Catonsville, Maryland; Howard University in Washington, D.C.; NASA’s Science Mission Directorate Planetary Science Division; NASA Ames; and NASA Goddard.

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

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

Lee esta historia en español aquí.

Some of Earth’s microbes likely to hitch a ride to space with human explorers could survive in the shaded nooks and crannies of the Moon’s South Pole region, NASA scientists say. 

Published on Aug. 19, 2026, in Science Advances, these findings highlight a need to better understand microbial persistence in extreme lunar environments. As humans build a permanent presence on the Moon, it may become difficult to distinguish ancient lunar chemistry from contamination delivered by visiting astronauts. The concern extends beyond the Moon and on to Mars, scientists say. 

“Humans are natural explorers, and with them come their voices, their memories … and their microbes,” said Prabal Saxena, a planetary scientist who led the study from NASA’s Goddard Space Flight Center in Greenbelt, Maryland. “For some scientists, myself included, that reality can be unsettling. But it also creates an opportunity to turn an imperfect situation into a useful experiment.”

Bringing microbes along is unavoidable: Humans have, on average, 1 million bacteria living on each patch of skin the size of a pencil eraser, for example. These bacteria vent from spacesuits and habitats. Though the paper’s authors worry about contamination interfering with the search for chemical clues to ancient geology or biology, they also argue that the Moon should be used as a natural lab. In shaded areas around the South Pole, scientists could carefully test the real-life limits of microbial survival in an environment that can’t easily be reproduced on Earth. 

Before any surface science can happen, scientists need a baseline measurement of what contaminants humans bring, the authors say.

“We need to understand what was there before us, because when we go to Mars to search for signs of life beyond our planet, we will want to make sure it’s not stuff we brought,” said Andrew Needham, a NASA Goddard-based paper co-author who is an Artemis contamination‑control scientist for lunar samples.

Even with strict sterilization procedures, some organisms are stubbornly resilient. A good example is Aspergillus niger, which is a fungus that thrives in warm, damp places like household bathrooms and heating, ventilation, and air conditioning systems. Astronauts have sampled it inside the International Space Station, and experiments demonstrate that the fungus can survive outside the station as well. Aspergillus niger was one of five microbes, including bacteria and fungi, selected for this study because of its known toughness in spaceflight environments. 

That microbes survived on the space station’s exterior surprised scientists. These species are typically not considered “extremophiles” that can withstand harsh conditions, such as the vacuum of space, according to Aaron Regberg, a geomicrobiologist at NASA’s Johnson Space Center in Houston.

“I would have expected these microbes to have dried out,” said Regberg, who studies space station bacteria and was a co-author on the paper.

He pointed out that NASA often bakes robotic spacecraft at temperatures above 400 degrees Fahrenheit to reduce the number of living organisms on them. But that’s not possible with astronauts, so contamination concerns take on new meaning in crewed exploration of the Moon’s south polar environment.

A clearer picture of where microbes might survive comes from understanding how sunlight behaves at the poles. Survival in this study means the microbe can stay alive for at least one Earth day, which does not mean that it can grow and reproduce.

Because the Moon has a very small tilt on its axis, the view from its poles is of a Sun that appears to hover just above the horizon, skimming the surface like a flashlight laying on a table. As a result, elevated parts of the surface, including crater ridges, mountains, and even small bumps, block light from reaching low-lying terrain. This produces pockets of shadowed areas that can remain cold and preserve water, as well as shield fragile molecules and possible microorganisms from lethal radiation.

With that scientific context in mind, the team set out to test which Earth microbes could survive extreme polar conditions. They focused on organisms commonly found in spaceflight environments and those common on human skin. Besides Aspergillus niger, these included Bacillus subtilis, Staphylococcus aureus, Deinococcus radiodurans, and several species of Fusarium. Based on an analysis of previous studies, the scientists noted the maximum amount of heat and ultraviolet (UV) radiation each organism can withstand.

Then, the organisms were tested in simulations of three regions near the lunar South Pole — Nobile Rim, Connecting Ridge, and De Gerlache Rim. Those simulations used detailed environmental maps built from elevation and temperature data collected by instruments aboard NASA’s Lunar Reconnaissance Orbiter, combined with models of how radiation strikes the surface.

The models showed maps of “survivable niches” that range in size from a miles-wide crater floor to an astronaut’s boot print. Aspergillus niger, which was most resistant to UV radiation, was able to survive even in areas with some sunlight exposure. UV radiation is so deadly to most microbes that it’s used for sterilization in hospitals. 

“When we think of the Moon, we don’t typically think of biology,” said Heather Graham, a paper co-author at NASA Goddard who helps develop tools and techniques for detecting biology that may look nothing like Earth’s. “But the Moon is a place where a cell can survive, so our first exploration of these sites should pay extra attention to our microbial hitchhikers and work hard to characterize lunar chemistry before our visits change what we will find.”

The authors note that while some microbes can survive in a dormant state in regions around the South Pole, and thereby confuse some future scientific investigations, there is no evidence the Moon has key ingredients to sustain growth and replication. Such ingredients include liquid water, which typically requires an atmosphere and moderate temperatures.  

For more information, visit:

https://science.nasa.gov/astrobiology

Observing across the starry “plains” of space, NASA’s James Webb Space Telescope has taken new images of NGC 2392, nicknamed the Lion Nebula. NASA’s Hubble Space Telescope previously viewed this planetary nebula in 2000, imaging the lion face-shaped target in visible light and revealing features such as the “mane” of hazy, comet-shaped objects. Now Webb has captured a clearer, more detailed view of the Lion Nebula due to its high-resolution imaging.

Lion Nebula (NIRCam and MIRI Image)

At first glance the nebula’s overall structure in Webb’s infrared images, with both the NIRCam (Near Infrared Camera) and MIRI (Mid Infrared Instrument) instruments, may look quite similar to Hubble’s earlier visible-light view. However, Webb’s infrared vision highlights features like compact clumps of dust and a haze of ionized gas. It’s taken several thousand years for this collection of gas and dust to reach its current shape, and the nebula’s components continue to be altered.

The source of these constant changes and the reason for the Lion Nebula’s distinct appearance is located at the center: the remains of a dying star. Though it looks like the button nose of the lion, its energy and radiation are powering the intricate structures seen here.

Lion Nebula (MIRI Image)

Massive stars undergo supernova explosions at the end of their lives, but these kinds of events are few and far in between. Most of the universe’s stars have lower masses, like the one belonging to NGC 2392. When a lower-mass star can no longer sustain itself with nuclear reactions in its core, the star becomes unstable and pulsates, losing its mass by shedding its outer layers, which then turn into shells of gas and dust called a planetary nebula. (Stars at this life stage are responsible for producing much of the universe’s observable dust.) The star’s radiation drives the ejected material away, leaving behind the very hot stellar core, also known as a white dwarf.

In the Lion Nebula’s case, the death of the oxygen-rich central star has left behind a white dwarf that is “cooking” everything from the inside and producing a bubble of ionized gas as it does. The gas bubble, which forms the lion’s face, is expanding over time and destroying dust that is in its path. Understanding why the swept-up gas has a complex structure of rings and shells, a common feature in planetary nebulae, is an ongoing endeavor.

The mane of the lion is the interior of a dust shell that is being illuminated by the white dwarf at the center. The tufts of hair, which look like cometary tails of material, are compact clumps of dust that have survived the stellar core’s radiation and protect the material that lies behind them.

Webb’s imagery “freezes” this planetary nebula in time, though the star’s death, and its tumultuous effects, go on. NGC 2392 will continue to undergo changes as its gas and dust migrate away from the stellar core. Astronomers estimate the lion will eventually disperse in approximately 10,000 years — a relatively short period in astronomical terms.

The James Webb Space Telescope is the world’s premier space science observatory. Webb is solving mysteries in our solar system, looking beyond to distant worlds around other stars, and probing the mysterious structures and origins of our universe and our place in it. Webb is an international program led by NASA with its partners, ESA (European Space Agency) and CSA (Canadian Space Agency).

To learn more about Webb, visit:

https://science.nasa.gov/webb

Downloads & Related Information

The following sections contain links to download this article’s images and videos in all available resolutions followed by related information links, media contacts, and if available, research paper and Spanish translation links.

Related Links

Explore more: Sonification of NGC 2392

View more: Hubble Image of NGC 2392

View more: Chandra X-ray Observatory Image of NGC 2392

More Webb: News | Images | Science | Home Page