Members Can Post Anonymously On This Site
Strange Probe seem to be searching for something in Buffalo, New York
-
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
7 min read
A New Alloy is Enabling Ultra-Stable Structures Needed for Exoplanet Discovery
A unique new material that shrinks when it is heated and expands when it is cooled could help enable the ultra-stable space telescopes that future NASA missions require to search for habitable worlds.
Advancements in material technologies are needed to meet the science needs of the next great observatories. These observatories will strive to find, identify, and study exoplanets and their ability to support life. Credit: NASA JPL One of the goals of NASA’s Astrophysics Division is to determine whether we are alone in the universe. NASA’s astrophysics missions seek to answer this question by identifying planets beyond our solar system (exoplanets) that could support life. Over the last two decades, scientists have developed ways to detect atmospheres on exoplanets by closely observing stars through advanced telescopes. As light passes through a planet’s atmosphere or is reflected or emitted from a planet’s surface, telescopes can measure the intensity and spectra (i.e., “color”) of the light, and can detect various shifts in the light caused by gases in the planetary atmosphere. By analyzing these patterns, scientists can determine the types of gasses in the exoplanet’s atmosphere.
Decoding these shifts is no easy task because the exoplanets appear very near their host stars when we observe them, and the starlight is one billion times brighter than the light from an Earth-size exoplanet. To successfully detect habitable exoplanets, NASA’s future Habitable Worlds Observatory will need a contrast ratio of one to one billion (1:1,000,000,000).
Achieving this extreme contrast ratio will require a telescope that is 1,000 times more stable than state-of-the-art space-based observatories like NASA’s James Webb Space Telescope and its forthcoming Nancy Grace Roman Space Telescope. New sensors, system architectures, and materials must be integrated and work in concert for future mission success. A team from the company ALLVAR is collaborating with NASA’s Marshall Space Flight Center and NASA’s Jet Propulsion Laboratory to demonstrate how integration of a new material with unique negative thermal expansion characteristics can help enable ultra-stable telescope structures.
Material stability has always been a limiting factor for observing celestial phenomena. For decades, scientists and engineers have been working to overcome challenges such as micro-creep, thermal expansion, and moisture expansion that detrimentally affect telescope stability. The materials currently used for telescope mirrors and struts have drastically improved the dimensional stability of the great observatories like Webb and Roman, but as indicated in the Decadal Survey on Astronomy and Astrophysics 2020 developed by the National Academies of Sciences, Engineering, and Medicine, they still fall short of the 10 picometer level stability over several hours that will be required for the Habitable Worlds Observatory. For perspective, 10 picometers is roughly 1/10th the diameter of an atom.
NASA’s Nancy Grace Roman Space Telescope sits atop the support structure and instrument payloads. The long black struts holding the telescope’s secondary mirror will contribute roughly 30% of the wave front error while the larger support structure underneath the primary mirror will contribute another 30%.
Credit: NASA/Chris Gunn
Funding from NASA and other sources has enabled this material to transition from the laboratory to the commercial scale. ALLVAR received NASA Small Business Innovative Research (SBIR) funding to scale and integrate a new alloy material into telescope structure demonstrations for potential use on future NASA missions like the Habitable Worlds Observatory. This alloy shrinks when heated and expands when cooled—a property known as negative thermal expansion (NTE). For example, ALLVAR Alloy 30 exhibits a -30 ppm/°C coefficient of thermal expansion (CTE) at room temperature. This means that a 1-meter long piece of this NTE alloy will shrink 0.003 mm for every 1 °C increase in temperature. For comparison, aluminum expands at +23 ppm/°C.
While other materials expand while heated and contract when cooled, ALLVAR Alloy 30 exhibits a negative thermal expansion, which can compensate for the thermal expansion mismatch of other materials. The thermal strain versus temperature is shown for 6061 Aluminum, A286 Stainless Steel, Titanium 6Al-4V, Invar 36, and ALLVAR Alloy 30.
Because it shrinks when other materials expand, ALLVAR Alloy 30 can be used to strategically compensate for the expansion and contraction of other materials. The alloy’s unique NTE property and lack of moisture expansion could enable optic designers to address the stability needs of future telescope structures. Calculations have indicated that integrating ALLVAR Alloy 30 into certain telescope designs could improve thermal stability up to 200 times compared to only using traditional materials like aluminum, titanium, Carbon Fiber Reinforced Polymers (CFRPs), and the nickel–iron alloy, Invar.
The hexapod assembly with six ALLVAR Alloy struts was measured for long-term stability. The stability of the individual struts and the hexapod assembly were measured using interferometry at the University of Florida’s Institute for High Energy Physics and Astrophysics. The struts were found to have a length noise well below the proposed target for the success criteria for the project. Credit: (left) ALLVAR and (right) Simon F. Barke, Ph.D. To demonstrate that negative thermal expansion alloys can enable ultra-stable structures, the ALLVAR team developed a hexapod structure to separate two mirrors made of a commercially available glass ceramic material with ultra-low thermal expansion properties. Invar was bonded to the mirrors and flexures made of Ti6Al4V—a titanium alloy commonly used in aerospace applications—were attached to the Invar. To compensate for the positive CTEs of the Invar and Ti6Al4V components, an NTE ALLVAR Alloy 30 tube was used between the Ti6Al4V flexures to create the struts separating the two mirrors. The natural positive thermal expansion of the Invar and Ti6Al4V components is offset by the negative thermal expansion of the NTE alloy struts, resulting in a structure with an effective zero thermal expansion.
The stability of the structure was evaluated at the University of Florida Institute for High Energy Physics and Astrophysics. The hexapod structure exhibited stability well below the 100 pm/√Hz target and achieved 11 pm/√Hz. This first iteration is close to the 10 pm stability required for the future Habitable Worlds Observatory. A paper and presentation made at the August 2021 Society of Photo-Optical Instrumentation Engineers conference provides details about this analysis.
Furthermore, a series of tests run by NASA Marshall showed that the ultra-stable struts were able to achieve a near-zero thermal expansion that matched the mirrors in the above analysis. This result translates into less than a 5 nm root mean square (rms) change in the mirror’s shape across a 28K temperature change.
The ALLVAR enabled Ultra-Stable Hexapod Assembly undergoing Interferometric Testing between 293K and 265K (right). On the left, the Root Mean Square (RMS) changes in the mirror’s surface shape are visually represented. The three roughly circular red areas are caused by the thermal expansion mismatch of the invar bonding pads with the ZERODUR mirror, while the blue and green sections show little to no changes caused by thermal expansion. The surface diagram shows a less than 5 nanometer RMS change in mirror figure. Credit: NASA’s X-Ray and Cryogenic Facility [XRCF] Beyond ultra-stable structures, the NTE alloy technology has enabled enhanced passive thermal switch performance and has been used to remove the detrimental effects of temperature changes on bolted joints and infrared optics. These applications could impact technologies used in other NASA missions. For example, these new alloys have been integrated into the cryogenic sub-assembly of Roman’s coronagraph technology demonstration. The addition of NTE washers enabled the use of pyrolytic graphite thermal straps for more efficient heat transfer. ALLVAR Alloy 30 is also being used in a high-performance passive thermal switch incorporated into the UC Berkeley Space Science Laboratory’s Lunar Surface Electromagnetics Experiment-Night (LuSEE Night) project aboard Firefly Aerospace’s Blue Ghost Mission 2, which will be delivered to the Moon through NASA’s CLPS (Commercial Lunar Payload Services) initiative. The NTE alloys enabled smaller thermal switch size and greater on-off heat conduction ratios for LuSEE Night.
Through another recent NASA SBIR effort, the ALLVAR team worked with NASA’s Jet Propulsion Laboratory to develop detailed datasets of ALLVAR Alloy 30 material properties. These large datasets include statistically significant material properties such as strength, elastic modulus, fatigue, and thermal conductivity. The team also collected information about less common properties like micro-creep and micro-yield. With these properties characterized, ALLVAR Alloy 30 has cleared a major hurdle towards space-material qualification.
As a spinoff of this NASA-funded work, the team is developing a new alloy with tunable thermal expansion properties that can match other materials or even achieve zero CTE. Thermal expansion mismatch causes dimensional stability and force-load issues that can impact fields such as nuclear engineering, quantum computing, aerospace and defense, optics, fundamental physics, and medical imaging. The potential uses for this new material will likely extend far beyond astronomy. For example, ALLVAR developed washers and spacers, are now commercially available to maintain consistent preloads across extreme temperature ranges in both space and terrestrial environments. These washers and spacers excel at counteracting the thermal expansion and contraction of other materials, ensuring stability for demanding applications.
For additional details, see the entry for this project on NASA TechPort.
Project Lead: Dr. James A. Monroe, ALLVAR
The following NASA organizations sponsored this effort: NASA Astrophysics Division, NASA SBIR Program funded by the Space Technology Mission Directorate (STMD).
Share
Details
Last Updated Jul 01, 2025 Related Terms
Technology Highlights Astrophysics Astrophysics Division Science-enabling Technology Explore More
7 min read NASA Webb ‘Pierces’ Bullet Cluster, Refines Its Mass
Article
1 day ago
2 min read Hubble Captures an Active Galactic Center
Article
4 days ago
2 min read NASA Citizen Scientists Find New Eclipsing Binary Stars
Article
5 days ago
View the full article
-
By European Space Agency
Video: 00:04:13 Daniel Neuenschwander, ESA head of Space and Robotic Exploration, explains that Ignis mission will include an ambitious technological and scientific programme with several experiments led by ESA and proposed by the Polish space industry.
On 26 June 2025, ESA project astronaut Sławosz Uznański-Wiśniewski from Poland and his crewmates arrived to the International Space Station on the Axiom-4 mission (Ax-4).
The Polish project astronaut is the second of a new generation of European astronauts to fly on a commercial human spaceflight opportunity with Axiom Space.
View the full article
-
By NASA
Curiosity Navigation Curiosity Home Mission Overview Where is Curiosity? Mission Updates Science Overview Instruments Highlights Exploration Goals News and Features Multimedia Curiosity Raw Images Images Videos Audio Mosaics More Resources Mars Missions Mars Sample Return Mars Perseverance Rover Mars Curiosity Rover MAVEN Mars Reconnaissance Orbiter Mars Odyssey More Mars Missions Mars Home 2 min read
Curiosity Blog, Sols 4580-4581: Something in the Air…
NASA’s Mars rover Curiosity acquired this image using its Left Navigation Camera on June 23, 2025 — Sol 4578, or Martian day 4,578 of the Mars Science Laboratory mission — at 02:38:50 UTC. NASA/JPL-Caltech Written by Scott VanBommel, Planetary Scientist at Washington University in St. Louis
Earth planning date: Monday, June 23, 2025
Curiosity was back at work on Monday, with a full slate of activities planned. While summer has officially arrived for much of Curiosity’s team back on Earth, Mars’ eldest active rover is recently through the depths of southern Mars winter and trending toward warmer temperatures itself. Warmer temperatures mean less component heating is required and therefore more power is freed up for science and driving. However, the current cooler temperatures do present an opportunity to acquire quality short-duration APXS measurements first thing in the morning, which is what Curiosity elected to do once again.
Curiosity’s plan commenced by brushing a rock target with potential cross-cutting veins, “Hornitos,” and subsequently analyzing it with APXS. A sequence of Mastcam images followed on targets such as “Volcán Peña Blanca,” “La Pacana,” “Iglesia de Jarinilla de Umatia,” and “Ayparavi.” ChemCam, returning to action after a brief and understood hiatus, rounded out the morning’s chemical analysis activities with a 5-point analysis of Ayparavi. After some images of the brush, and a handful of MAHLI snaps of Hornitos, Curiosity was on its way with a planned drive of about 37 meters (about 121 feet).Curiosity’s night would not be spent entirely dreaming of whatever rovers dream, but rather conducting a lengthy APXS analysis of the atmosphere. These analyses enable Curiosity’s team to assess the abundance of argon in the atmosphere — from a volume about the size of a pop can (or soda can, depending on your unit of preference) — which can be used to trace global circulation patterns and better understand modern Mars. Recently, Curiosity has been increasing the frequency of these measurements and pairing them with ChemCam “Passive Sky” observations. These ChemCam activities do not utilize the instrument’s laser, but instead use its other components to characterize the air above the rover. By combining APXS and ChemCam observations of the atmosphere, Curiosity’s team is able to better assess daily and seasonal trends in gases around Gale crater. A ChemCam “Passive Sky” was the primary observation in the second sol of the plan, with Curiosity spending much of the remaining time recharging and eagerly awaiting commands from Wednesday’s team.
For more Curiosity blog posts, visit MSL Mission Updates
Learn more about Curiosity’s science instruments
Share
Details
Last Updated Jun 26, 2025 Related Terms
Blogs Explore More
2 min read Clay Minerals From Mars’ Most Ancient Past?
Article
3 days ago
4 min read Curiosity Blog, Sols 4577-4579: Watch the Skies
Article
6 days ago
2 min read Curiosity Blog, Sols 4575-4576: Perfect Parking Spot
Article
6 days ago
Keep Exploring Discover More Topics From NASA
Mars
Mars is the fourth planet from the Sun, and the seventh largest. It’s the only planet we know of inhabited…
All Mars Resources
Explore this collection of Mars images, videos, resources, PDFs, and toolkits. Discover valuable content designed to inform, educate, and inspire,…
Rover Basics
Each robotic explorer sent to the Red Planet has its own unique capabilities driven by science. Many attributes of a…
Mars Exploration: Science Goals
The key to understanding the past, present or future potential for life on Mars can be found in NASA’s four…
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.