Members Can Post Anonymously On This Site
Process over outcome: Guardian makes history as Top BMT Graduate
-
Similar Topics
-
By NASA
6 min read
Smarter Searching: NASA AI Makes Science Data Easier to Find
Image snapshot taken from NASA Worldview of NASA’s Global Precipitation Measurement (GPM) mission on March 15, 2025 showing heavy rain across the southeastern U.S. with an overlay of the GCMD Keyword Recommender for Earth Science, Atmosphere, Precipitation, Droplet Size. NASA Worldview Imagine shopping for a new pair of running shoes online. If each seller described them differently—one calling them “sneakers,” another “trainers,” and someone else “footwear for exercise”—you’d quickly feel lost in a sea of mismatched terminology. Fortunately, most online stores use standardized categories and filters, so you can click through a simple path: Women’s > Shoes > Running Shoes—and quickly find what you need.
Now, scale that problem to scientific research. Instead of sneakers, think “aerosol optical depth” or “sea surface temperature.” Instead of a handful of retailers, it is thousands of researchers, instruments, and data providers. Without a common language for describing data, finding relevant Earth science datasets would be like trying to locate a needle in a haystack, blindfolded.
That’s why NASA created the Global Change Master Directory (GCMD), a standardized vocabulary that helps scientists tag their datasets in a consistent and searchable way. But as science evolves, so does the challenge of keeping metadata organized and discoverable.
To meet that challenge, NASA’s Office of Data Science and Informatics (ODSI) at the agency’s Marshall Space Flight Center (MSFC) in Huntsville, Alabama, developed the GCMD Keyword Recommender (GKR): a smart tool designed to help data providers and curators assign the right keywords, automatically.
Smarter Tagging, Accelerated Discovery
The upgraded GKR model isn’t just a technical improvement; it’s a leap forward in how we organize and access scientific knowledge. By automatically recommending precise, standardized keywords, the model reduces the burden on human curators while ensuring metadata quality remains high. This makes it easier for researchers, students, and the public to find exactly the datasets they need.
It also sets the stage for broader applications. The techniques used in GKR, like applying focal loss to rare-label classification problems and adapting pre-trained transformers to specialized domains, can benefit fields well beyond Earth science.
Metadata Matchmaker
The newly upgraded GKR model tackles a massive challenge in information science known as extreme multi-label classification. That’s a mouthful, but the concept is straightforward: Instead of predicting just one label, the model must choose many, sometimes dozens, from a set of thousands. Each dataset may need to be tagged with multiple, nuanced descriptors pulled from a controlled vocabulary.
Think of it like trying to identify all the animals in a photograph. If there’s just a dog, it’s easy. But if there’s a dog, a bird, a raccoon hiding behind a bush, and a unicorn that only shows up in 0.1% of your training photos, the task becomes far more difficult. That’s what GKR is up against: tagging complex datasets with precision, even when examples of some keywords are scarce.
And the problem is only growing. The new version of GKR now considers more than 3,200 keywords, up from about 430 in its earlier iteration. That’s a sevenfold increase in vocabulary complexity, and a major leap in what the model needs to learn and predict.
To handle this scale, the GKR team didn’t just add more data; they built a more capable model from the ground up. At the heart of the upgrade is INDUS, an advanced language model trained on a staggering 66 billion words drawn from scientific literature across disciplines—Earth science, biological sciences, astronomy, and more.
NASA ODSI’s GCMD Keyword Recommender AI model automatically tags scientific datasets with the help of INDUS, a large language model trained on NASA scientific publications across the disciplines of astrophysics, biological and physical sciences, Earth science, heliophysics, and planetary science. NASA “We’re at the frontier of cutting-edge artificial intelligence and machine learning for science,” said Sajil Awale, a member of the NASA ODSI AI team at MSFC. “This problem domain is interesting, and challenging, because it’s an extreme classification problem where the model needs to differentiate even very similar keywords/tags based on small variations of context. It’s exciting to see how we have leveraged INDUS to build this GKR model because it is designed and trained for scientific domains. There are opportunities to improve INDUS for future uses.”
This means that the new GKR isn’t just guessing based on word similarities; it understands the context in which keywords appear. It’s the difference between a model knowing that “precipitation” might relate to weather versus recognizing when it means a climate variable in satellite data.
And while the older model was trained on only 2,000 metadata records, the new version had access to a much richer dataset of more than 43,000 records from NASA’s Common Metadata Repository. That increased exposure helps the model make more accurate predictions.
The Common Metadata Repository is the backend behind the following data search and discovery services:
Earthdata Search International Data Network Learning to Love Rare Words
One of the biggest hurdles in a task like this is class imbalance. Some keywords appear frequently; others might show up just a handful of times. Traditional machine learning approaches, like cross-entropy loss, which was used initially to train the model, tend to favor the easy, common labels, and neglect the rare ones.
To solve this, NASA’s team turned to focal loss, a strategy that reduces the model’s attention to obvious examples and shifts focus toward the harder, underrepresented cases.
The result? A model that performs better across the board, especially on the keywords that matter most to specialists searching for niche datasets.
From Metadata to Mission
Ultimately, science depends not only on collecting data, but on making that data usable and discoverable. The updated GKR tool is a quiet but critical part of that mission. By bringing powerful AI to the task of metadata tagging, it helps ensure that the flood of Earth observation data pouring in from satellites and instruments around the globe doesn’t get lost in translation.
In a world awash with data, tools like GKR help researchers find the signal in the noise and turn information into insight.
Beyond powering GKR, the INDUS large language model is also enabling innovation across other NASA SMD projects. For example, INDUS supports the Science Discovery Engine by helping automate metadata curation and improving the relevancy ranking of search results.The diverse applications reflect INDUS’s growing role as a foundational AI capability for SMD.
The INDUS large language model is funded by the Office of the Chief Science Data Officer within NASA’s Science Mission Directorate at NASA Headquarters in Washington. The Office of the Chief Science Data Officer advances scientific discovery through innovative applications and partnerships in data science, advanced analytics, and artificial intelligence.
Share
Details
Last Updated Jul 09, 2025 Related Terms
Science & Research Artificial Intelligence (AI) Explore More
2 min read Polar Tourists Give Positive Reviews to NASA Citizen Science in Antarctica
Article
6 hours ago
2 min read Hubble Observations Give “Missing” Globular Cluster Time to Shine
Article
6 days ago
5 min read How NASA’s SPHEREx Mission Will Share Its All-Sky Map With the World
Article
7 days ago
Keep Exploring Discover Related Topics
Missions
Humans in Space
Climate Change
Solar System
View the full article
-
By Space Force
Col. Nick Hague, the first Guardian to launch into space, visited Vandenberg Space Force Base.
View the full article
-
By NASA
7 min read
Preparations for Next Moonwalk Simulations Underway (and Underwater)
In the summer 2025 issue of the NASA History Office’s News & Notes newsletter, examples of leadership and critical decision-making in NASA’s history form the unifying theme. Among the topics discussed are NASA’s Shuttle-Centaur program, assessing donations to the NASA Archives, how the discovery of the first exoplanet orbiting a sun-like star catalyzed NASA’s exoplanet program, and Chief of the Medical Operations Office Charles A. Berry’s decisions surrounding crew health when planning the Project Gemini missions.
Volume 42, Number 2
Summer 2025
Featured Articles
From the Chief Historian
By Brian Odom
NASA’s is a history marked by critical decisions. From George Mueller’s 1963 decision for “all up” testing of the Saturn V rocket to Michael Griffin’s 2006 decision to launch a final servicing mission to the Hubble Space Telescope, the agency has continually met key inflection points with bold decisions. These choices, such as the decision to send a crewed Apollo 8 mission around the Moon in December 1968, stand at the center of the agency’s national legacy and promote confidence in times of crisis. Continue Reading
Shuttle-Centaur: Loss of Launch Vehicle Redundancy Leads to Discord
By Robert Arrighi
“Although the Shuttle/Centaur decision was very difficult to make, it is the proper thing to do, and this is the time to do it.” With those words on June 19, 1986, NASA Administrator James Fletcher canceled the intensive effort to integrate the Centaur upper stage with the Space Shuttle to launch the Galileo and Ulysses spacecraft. The decision, which was tied to increased safety measures following the loss of Challenger several months earlier, brought to the forefront the 1970s decision to launch all U.S. payloads with the Space Shuttle. Continue Reading
Lewis Director Andy Stofan speaks at the Shuttle-Centaur rollout ceremony on August 23, 1985 at General Dynamics’s San Diego headquarters. Galileo mission crew members Dave Walker, Rick Hauck, and John Fabian were among those on stage. NASA A View into NASA’s Response to the Apollo 1 Tragedy
By Kate Mankowski
On January 27, 1967, Mission AS-204 (later known as Apollo 1) was conducting a simulated countdown when a fire suddenly broke out in the spacecraft, claiming the lives of astronauts Virgil I. “Gus” Grissom, Edward H. White, and Roger B. Chaffee. The disaster highlighted the risks that come with spaceflight and the work that still needed to be accomplished to meet President Kennedy’s challenge of going to the Moon before the end of the decade. With the complexity of the Apollo spacecraft, discerning the cause of the fire proved to be incredibly difficult. Continue Reading
The Fight to Fund AgRISTARS
By Brad Massey
Robert MacDonald, the manager of NASA’s Large Area Crop Inventory Experiment (LACIE), was not pleased in January 1978 after he read a draft copy of the U.S. General Accounting Office’s (GAO’s) “Crop Forecasting by Satellite: Progress and Problems” report. The draft’s authors argued that LACIE had not achieved its goals of accurately predicting harvest yields in the mid-1970s. Therefore, congressional leaders should “be aware of the disappointing performance of LACIE to date when considering the future direction of NASA’s Landsat program and the plans of the Department of Agriculture.” Continue Reading
The Hubble Space Telescope: The Right Project at the Right Time
By Jillian Rael
This year, NASA commemorates 35 years of the Hubble Space Telescope’s study of the cosmos. From observations of never-before-seen phenomena within our solar system, to the discovery of distant galaxies, the confirmation of the existence of supermassive black holes, and precision measurements of the universe’s expansion, Hubble has made incredible contributions to science, technology, and even art. Yet, for all its contemporary popularity, the Hubble program initially struggled for congressional approval and consequential funding. For its part, NASA found new ways to compromise and cut costs, while Congress evaluated national priorities and NASA’s other space exploration endeavors against the long-range value of Hubble. Continue Reading
Within the tempestuous Carina Nebula lies “Mystic Mountain.”NASA/ESA/M. Livio/Hubble 20th Anniversary Team Appraisal: The Science and Art of Assessing Donations to the NASA Archives
By Alan Arellano
The major functions of an archivist center include appraising, arranging, describing, preserving, and providing access to historical records and documents. While together these are pillars of archival science, they are more of an art than a science in their application, fundamentally necessitating skilled decision making. Throughout the NASA archives, staff members make these decisions day in and day out. Continue Reading
Orbit Shift: How 50 Pegasi b Helped Pull NASA Toward the Stars in the 1990s
By Lois Rosson
On October 20, 1995, the New York Times reported the detection of a distant planet orbiting a Sun-like star. The star, catalogued as 51 Pegasi by John Flamsteed in the 18th century, was visible to the naked eye as part of the constellation Pegasus—and had wobbled on its axis just enough that two Swiss astronomers were able to deduce the presence of another object exerting its gravitational pull on the star’s rotation. The discovery was soon confirmed by other astronomers, and 51 Pegasi b was heralded as the first confirmed exoplanet orbiting a star similar to our own Sun. Continue Reading
Detail from an infographic about 51 Pegasi b and the significance of its discovery.NASA Four, Eight, Fourteen Days: Charles A. Berry, Gemini, and the Critical Steps to Living and Working in Space
By Jennifer Ross-Nazzal
In 1963, critical decisions had to be made about NASA’s upcoming Gemini missions if the nation were to achieve President John F. Kennedy’s lunar goals. Known as the bridge to Apollo, Project Gemini was critical to landing a man on the Moon by the end of the decade and returning him safely to Earth. The project would demonstrate that astronauts could rendezvous and dock their spacecraft to another space vehicle and give flight crews the opportunity to test the planned extravehicular capabilities in preparation for walking on the lunar surface on future Apollo flights. Perhaps most importantly, Gemini had to show that humans could live and work in space for long periods of time, a fiercely debated topic within and outside of the agency. Continue Reading
Dr. Charles Berry prepares to check the blood pressure of James A. McDivitt, Command Pilot for the Gemini IV mission. McDivitt is on the tilt table at the Aero Medical Area, Merritt Island, FL, where he and Gemini IV pilot Edward H. White II underwent preflight physicals in preparation for their four-day spaceflight.NASA Imagining Space: The Life and Art of Robert McCall
By Sandra Johnson
As we walked into Bob McCall’s Arizona home, it quickly became obvious that two talented and creative people lived there. Tasked with interviewing one of the first artists to be invited to join the NASA Art Program, our oral history team quickly realized the session with McCall would include a unique perspective on NASA’s history. We traveled to Arizona in the spring of 2000 to capture interviews with some of the pioneers of spaceflight and had already talked to an eclectic group of subjects in their homes, including a flight controller for both Gemini and Apollo, an astronaut who had flown on both Skylab and Space Shuttle missions, a former NASA center director, and two former Women’s Airforce Service Pilots (WASPs) who ferried airplanes during WWII. However, unlike most interviews, the setting itself provided a rare glimpse into the man and his inspiration. Continue Reading
Inside the Archives: Biomedical Branch Files
By Alejandra Lopez
The Biomedical Branch Files (1966–2008) in the Johnson Space Center archives showcase the inner workings of a NASA office established to perform testing to provide a better understanding of the impacts of spaceflight on the human body. Ranging from memos and notes to documents and reports, this collection is an invaluable resource on the biomedical research done with NASA’s Apollo, Skylab, Space Shuttle, and Space Station projects. Files in the collection cover work done by groups within the branch such as the Toxicology, Microbiology, Clinical, and Biochemistry Laboratories. It also reveals the branch’s evolution and changes in its decision-making process over the years. Continue Reading
Dr. Carolyn S. Huntoon, shown here in 1972, became the Biomedical Branch’s first chief in 1977.NASA Download the Summer 2025 Edition More Issues of NASA History News and Notes Share
Details
Last Updated Jun 20, 2025 EditorMichele Ostovar Related Terms
NASA History Newsletters Explore More
5 min read NASA History News and Notes–Spring 2025
Article 3 months ago 6 min read NASA History News and Notes – Winter 2024
Article 6 months ago 7 min read NASA History News and Notes – Fall 2024
Article 9 months ago Keep Exploring Discover Related Topics
NASA History
History Publications and Resources
NASA Archives
NASA Oral Histories
View the full article
-
By USH
Some time ago, while visiting the Grand Canyon in Arizona, a photographer captured several short video clips of the landscape. In one of those clips, an unusual anomaly was discovered.
The original footage is only 1.9 seconds long, but within that moment, something remarkable was caught on camera. An unidentified aerial phenomenon (UAP) flashed across the frame, visible for less than a second, only noticeable when the video was paused and analyzed frame by frame.
The object was moving at an astonishing speed, covering an estimated two to three miles in under a second, far beyond the capabilities of any conventional aircraft, drone, or helicopter.
This isn’t the first time such anomalous flying objects have been observed. Their characteristics defy comparison with known aerial technology.
Some skeptics have proposed that the object might have been a rock thrown into the canyon from behind the camera. However, that explanation seems unlikely. Most people can only throw objects at speeds of 10 to 20 meters per second (approximately 22 to 45 mph). The velocity of this object far exceeded that range, and its near-invisibility in the unedited video suggests it was moving much faster.
View the full article
-
By Space Force
Second Lt. Katherine Hendl escorted the remains of her great-great-uncle, a U.S. Army Air Forces gunner killed in action during World War II, home to Massachusetts nearly 80 years after he was declared missing in action.
View the full article
-
-
Check out these Videos
Recommended Posts
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.