Members Can Post Anonymously On This Site
Hubble Makes Surprising Find in the Early Universe
-
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 NASA
As Hubble marks three and a half decades of scientific breakthroughs and technical resilience, the “Hubble at 35 Years” symposium offers a platform to reflect on the mission’s historical, operational, and scientific legacy. Hubble’s trajectory—from early challenges to becoming a symbol of American scientific ingenuity—presents valuable lessons in innovation, collaboration, and crisis response. Bringing together scientists, engineers, and historians at NASA Headquarters ensures that this legacy informs current and future mission planning, including operations for the James Webb Space Telescope, Roman Space Telescope, and other next-generation observatories. The symposium not only honors Hubble’s transformative contributions but also reinforces NASA’s commitment to learning from the past to shape a more effective and ambitious future for space science.
Hubble at 35 Years
Lessons Learned in Scientific Discovery and NASA Flagship Mission Operations
October 16–17, 2025
James Webb Auditorium, NASA HQ, Washington, D.C.
The giant Hubble Space Telescope (HST) can be seen as it is suspended in space by Discovery’s Remote Manipulator System (RMS) following the deployment of part of its solar panels and antennae on April 25, 1990.NASA The story of the Hubble Space Telescope confirms its place as the most transformative and significant astronomical observatory in history. Once called “the eighth wonder of the world” by a former NASA administrator, Hubble’s development since its genesis in the early 1970s and its launch, repair, and ultimate impact since 1990 provide ample opportunity to apply insights from its legacy. Scientists and engineers associated with groundbreaking discoveries have always operated within contexts shaped by forces including the government, private industry, the military, and the public at large. The purpose of this symposium is to explore the insights from Hubble’s past and draw connections that can inform the development of mission work today and for the future.
Contact the Organizer Keep Exploring Discover More Topics From NASA
Hubble’s 35th Anniversary
Universe
Humans In Space
NASA History
View the full article
-
By NASA
Explore Hubble Hubble Home Overview About Hubble The History of Hubble Hubble Timeline Why Have a Telescope in Space? Hubble by the Numbers At the Museum FAQs Science Hubble Science Science Themes Science Highlights Science Behind Discoveries Hubble’s Partners in Science Universe Uncovered Hubble and Artificial Intelligence Explore the Night Sky Impact & Benefits Hubble’s Impact & Benefits Science Impacts Cultural Impact Technology Benefits Impact on Human Spaceflight Astro Community Impacts Observatory Hubble Observatory Hubble Design Mission Operations Missions to Hubble Hubble vs Webb Team Hubble Team Career Aspirations Hubble Astronauts Multimedia Images Videos Sonifications Podcasts e-Books Online Activities 3D Hubble Models Lithographs Fact Sheets Posters Hubble on the NASA App Glossary News Hubble News Social Media Media Resources More 35th Anniversary Online Activities 2 min read
Hubble Observations Give “Missing” Globular Cluster Time to Shine
This NASA Hubble Space Telescope image features a dense and dazzling array of blazing stars that form globular cluster ESO 591-12. NASA, ESA, and D. Massari (INAF — Osservatorio di Astrofisica e Scienza dello Spazio); Processing: Gladys Kober (NASA/Catholic University of America)
Download this image
A previously unexplored globular cluster glitters with multicolored stars in this NASA Hubble Space Telescope image. Globular clusters like this one, called ESO 591-12 or Palomar 8, are spherical collections of tens of thousands to millions of stars tightly bound together by gravity. Globular clusters generally form early in the galaxies’ histories in regions rich in gas and dust. Since the stars form from the same cloud of gas as it collapses, they typically hover around the same age. Strewn across this image of ESO 591-12 are a number of red and blue stars. The colors indicate their temperatures; red stars are cooler, while the blue stars are hotter.
Hubble captured the data used to create this image of ESO 591-12 as part of a study intended to resolve individual stars of the entire globular cluster system of the Milky Way. Hubble revolutionized the study of globular clusters since earthbound telescopes are unable to distinguish individual stars in the compact clusters. The study is part of the Hubble Missing Globular Clusters Survey, which targets 34 confirmed Milky Way globular clusters that Hubble has yet to observe.
The program aims to provide complete observations of ages and distances for all of the Milky Way’s globular clusters and investigate fundamental properties of still-unexplored clusters in the galactic bulge or halo. The observations will provide key information on the early stages of our galaxy, when globular clusters formed.
Explore More
Hubble’s Star Clusters
Exploring the Birth of Stars
Facebook logo @NASAHubble @NASAHubble Instagram logo @NASAHubble Media Contact:
Claire Andreoli
NASA’s Goddard Space Flight Center, Greenbelt, MD
claire.andreoli@nasa.gov
Share
Details
Last Updated Jul 03, 2025 Editor Andrea Gianopoulos Location NASA Goddard Space Flight Center Related Terms
Hubble Space Telescope Astrophysics Astrophysics Division Galaxies, Stars, & Black Holes Globular Clusters Goddard Space Flight Center Star Clusters Stars Keep Exploring Discover More Topics From Hubble
Hubble Space Telescope
Since its 1990 launch, the Hubble Space Telescope has changed our fundamental understanding of the universe.
Hubble’s Cosmic Adventure
Hubble’s Night Sky Challenge
Hubble’s 35th Anniversary
View the full article
-
By NASA
ESA/Hubble & NASA, M. J. Koss, A. J. Barth The light that the NASA/ESA Hubble Space Telescope collected to create this image reached the telescope after a journey of 250 million years. Its source was the spiral galaxy UGC 11397, which resides in the constellation Lyra (The Lyre). At first glance, UGC 11397 appears to be an average spiral galaxy: it sports two graceful spiral arms that are illuminated by stars and defined by dark, clumpy clouds of dust.
What sets UGC 11397 apart from a typical spiral lies at its center, where a supermassive black hole containing 174 million times the mass of our Sun grows. As a black hole ensnares gas, dust, and even entire stars from its vicinity, this doomed matter heats up and puts on a fantastic cosmic light show.
Material trapped by the black hole emits light from gamma rays to radio waves, and can brighten and fade without warning. But in some galaxies, including UGC 11397, thick clouds of dust hide much of this energetic activity from view in optical light. Despite this, UGC 11397’s actively growing black hole was revealed through its bright X-ray emission — high-energy light that can pierce the surrounding dust. This led astronomers to classify it as a Type 2 Seyfert galaxy, a category used for active galaxies whose central regions are hidden from view in visible light by a donut-shaped cloud of dust and gas.
Using Hubble, researchers will study hundreds of galaxies that, like UGC 11397, harbor a supermassive black hole that is gaining mass. The Hubble observations will help researchers weigh nearby supermassive black holes, understand how black holes grew early in the universe’s history, and even study how stars form in the extreme environment found at the very center of a galaxy.
Text credit: ESA
Image credit: ESA/Hubble & NASA, M. J. Koss, A. J. Barth
View the full article
-
By NASA
2 min read
Hubble Captures an Active Galactic Center
This Hubble image shows the spiral galaxy UGC 11397. ESA/Hubble & NASA, M. J. Koss, A. J. Barth The light that the NASA/ESA Hubble Space Telescope collected to create this image reached the telescope after a journey of 250 million years. Its source was the spiral galaxy UGC 11397, which resides in the constellation Lyra (The Lyre). At first glance, UGC 11397 appears to be an average spiral galaxy: it sports two graceful spiral arms that are illuminated by stars and defined by dark, clumpy clouds of dust.
What sets UGC 11397 apart from a typical spiral lies at its center, where a supermassive black hole containing 174 million times the mass of our Sun grows. As a black hole ensnares gas, dust, and even entire stars from its vicinity, this doomed matter heats up and puts on a fantastic cosmic light show.
Material trapped by the black hole emits light from gamma rays to radio waves, and can brighten and fade without warning. But in some galaxies, including UGC 11397, thick clouds of dust hide much of this energetic activity from view in optical light. Despite this, UGC 11397’s actively growing black hole was revealed through its bright X-ray emission — high-energy light that can pierce the surrounding dust. This led astronomers to classify it as a Type 2 Seyfert galaxy, a category used for active galaxies whose central regions are hidden from view in visible light by a donut-shaped cloud of dust and gas.
Using Hubble, researchers will study hundreds of galaxies that, like UGC 11397, harbor a supermassive black hole that is gaining mass. The Hubble observations will help researchers weigh nearby supermassive black holes, understand how black holes grew early in the universe’s history, and even study how stars form in the extreme environment found at the very center of a galaxy.
Facebook logo @NASAHubble @NASAHubble Instagram logo @NASAHubble Media Contact:
Claire Andreoli (claire.andreoli@nasa.gov)
NASA’s Goddard Space Flight Center, Greenbelt, MD
Share
Details
Last Updated Jun 27, 2025 Related Terms
Hubble Space Telescope Keep Exploring Discover More Topics From Hubble
Hubble Space Telescope
Since its 1990 launch, the Hubble Space Telescope has changed our fundamental understanding of the universe.
Hubble’s Galaxies
Galaxy Details and Mergers
Hubble’s Night Sky Challenge
View the full article
-
-
Similar Videos
-
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.