Members Can Post Anonymously On This Site
-
Similar Topics
-
-
By NASA
Explore This Section Science Goddard Space Flight Center Linking Satellite Data and… Overview Learning Resources Science Activation Teams SME Map Opportunities More Science Activation Stories Citizen Science 4 min read
Linking Satellite Data and Community Knowledge to Advance Alaskan Snow Science
Seasonal snow plays a significant role in global water and energy cycles, and billions of people worldwide rely on snowmelt for water resources needs, including water supply, hydropower, agriculture, and more. Monitoring snow water equivalent (SWE) is critical for supporting these applications and for mitigating damages caused by snowmelt flooding, avalanches, and other snow-related disasters. However, our ability to measure SWE remains a challenge, particularly in northern latitudes where in situ SWE observations are sparse and satellite observations are impacted by the boreal forest and environmental conditions. Despite limited in situ SWE measurements, local residents in Arctic and sub-Arctic regions provide a vast and valuable body of place-based knowledge and observations that are essential for understanding snowpack behavior in northern regions.
As part of a joint NASA SnowEx, NASA’s Minority University Research and Education Project (MUREP) for American Indian and Alaska Native STEM (Science, Technology, Engineering, & Mathematics) Engagement (MAIANSE), and Global Learning & Observations to Benefit the Environment (GLOBE) Program partnership, a team of scientists including NASA intern Julia White (NASA Goddard Space Flight Center, University of Alaska Fairbanks), Carrie Vuyovich (NASA Goddard Space Flight Center), Alicia Joseph (NASA Goddard Space Flight Center), and Christi Buffington (University of Alaska Fairbanks, GLOBE Implementation Office) is studying snow water equivalent (SWE) across Interior Alaska. This project combines satellite-based interferometric synthetic aperture radar (InSAR) data, primarily from the Sentinel-1 satellite, with ground-based observations from the Snow Telemetry (SNOTEL) network and GLOBE (Global Learning Observations to Benefit the Environment). Together, these data sources help the team investigate how SWE varies across the landscape and how it affects local ecosystems and communities. The team is also preparing for future integration of data from NASA’s upcoming NISAR (NASA ISRO Synthetic Aperture Radar) mission, which is expected to enhance SWE retrieval capabilities.
After a collaborative visit to the classroom of Tammie Kovalenko in November 2024, Delta Junction junior and senior high school students in vocational agriculture (Vo Ag) classes, including members of Future Farmers of America (FFA), began collecting GLOBE data on a snowdrift located just outside their classroom. As the project progressed, students developed their own research questions. One student, Fianna Rooney, took the project even further — presenting research posters at both the GLOBE International Virtual Science Symposium (IVSS) and both the FFA Regional and National Conventions. Her work highlights the growing role of Alaskan youth in science, and how student-led inquiry can enrich both education and research outcomes. (This trip was funded by the NASA Science Activation Program’s Arctic and Earth SIGNs – STEM Integrating GLOBE & NASA – project at the University of Alaska Fairbanks.)
In February 2025, the team collaborated with Delta Junction Junior High and High School students, along with the Delta Junction Trails Association, to conduct a GLOBE Intensive Observation Period (IOP), “Delta Junction Snowdrifts,” to collect Landcover photos, snow depth, and snow water equivalent data. Thanks to aligned interests and research goals at the Alaska Satellite Facility (ASF), the project was further expanded into Spring 2025. Collaborators from ASF and the Alaska Center for Unmanned Aircraft Systems Integration (ACUASI) collected high resolution airborne data over the snowdrift at the Delta Junction Junior and Senior High School. This complementary dataset helped strengthen connections between satellite observations and ground-based student measurements.
This effort, led by a NASA intern, scientists, students, and Alaskan community members, highlights the power of collaboration in advancing science and education. Next steps will include collaboration with Native Alaskan communities near Delta Junction, including the Healy Lake Tribe, whose vast, generational knowledge will be of great value to deepening our understanding of Alaskan snow dynamics.
Learn more about how NASA’s Science Activation program connects NASA science experts, real content, and experiences with community leaders to do science in ways that activate minds and promote deeper understanding of our world and beyond: https://science.nasa.gov/learn/about-science-activation/
Julia White and Delta Junction student following GLOBE protocols for snow depth. Tori Brannan Share
Details
Last Updated Jul 14, 2025 Editor NASA Science Editorial Team Location Goddard Space Flight Center Related Terms
Earth Science Goddard Space Flight Center MUREP Science Activation Explore More
2 min read Hubble Snaps Galaxy Cluster’s Portrait
Article
3 days ago
7 min read NASA’s Parker Solar Probe Snaps Closest-Ever Images to Sun
On its record-breaking pass by the Sun late last year, NASA’s Parker Solar Probe captured…
Article
4 days ago
8 min read NASA’s Webb Scratches Beyond Surface of Cat’s Paw for 3rd Anniversary
Article
4 days ago
Keep Exploring Discover More Topics From NASA
James Webb Space Telescope
Webb is the premier observatory of the next decade, serving thousands of astronomers worldwide. It studies every phase in the…
Perseverance Rover
This rover and its aerial sidekick were assigned to study the geology of Mars and seek signs of ancient microbial…
Parker Solar Probe
On a mission to “touch the Sun,” NASA’s Parker Solar Probe became the first spacecraft to fly through the corona…
Juno
NASA’s Juno spacecraft entered orbit around Jupiter in 2016, the first explorer to peer below the planet’s dense clouds to…
View the full article
-
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
Earth (ESD) Earth Explore Explore Earth Home Air Quality Climate Change Freshwater Life on Earth Severe Storms Snow and Ice The Global Ocean Science at Work Earth Science at Work Technology and Innovation Powering Business Multimedia Image Collections Videos Data For Researchers About Us 4 min read
NASA-Assisted Scientists Get Bird’s-Eye View of Population Status
Through the eBird citizen scientist program, millions of birders have recorded their observations of different species and submitted checklists to the Cornell Lab of Ornithology. Through a partnership with NASA, the lab has now used this data to model and map bird population trends for nearly 500 North American species.
Led by Alison Johnston of the University of St. Andrews in Scotland, the researchers reported that 75% of bird species in the study are declining at wide-range scales. And yet this study has some good news for birds. The results, published in Science in May, offer insights and projections that could shape the future conservation of the places where birds make their homes.
“This project demonstrates the power of merging in situ data with NASA remote sensing to model biological phenomena that were previously impossible to document,” said Keith Gaddis, NASA’s Biological Diversity and Ecological Forecasting program manager at the agency’s headquarters in Washington, who was not involved in the study. “This data provides not just insight into the Earth system but also provides actionable guidance to land managers to mitigate biodiversity loss.”
Rock wren in Joshua Tree National Park. National Park Service / Jane Gamble A team from Cornell, the University of St. Andrews, and the American Bird Conservancy used land imaging data from NASA’s Moderate Resolution Imaging Spectroradiometer (MODIS) instruments to distinguish among such specific bird habitats as open forests, dense shrublands, herbaceous croplands, and forest/cropland mosaics. They also drew on NASA weather information and water data that matched the dates and times when birders made their reports.
When combined with a 14-year set of eBird checklists — 36 million sets of species observations and counts, keyed directly to habitats — the satellite data gave researchers almost a strong foundation to produce a clear picture of the health of bird populations. But there was one missing piece.
Wrestling with Wren Data
While some eBird checklists come from expert birders who’ve hiked deep into wildlife preserves, others are sent in by novices watching bird feeders and doing the dishes. This creates what Cornell statistician Daniel Fink described as “an unstructured, very noisy data set,” complete with gaps in the landscape that birders did not reach and, ultimately, some missing birds.
To account for gaps where birds weren’t counted, the researchers trained machine learning models to fill in the maps based on the remote sensing data. “For every single species — say the rock wren — we’ve created a simulation that mimics the species and a variety of ways that it could respond to changes in the environment,” Johnston said. “Thousands of simulations underlie the results we showed.”
CornellLab eBird The researchers achieved unprecedented resolution, zeroing in on areas 12 miles by 12 miles (27 km by 27 km), the same area as Portland, Oregon. This new population counting method can also be applied to eBird data from other locations, Fink said. “Now we’re using modeling to track bird populations — not seasonally through the year, but acrossthe years — a major milestone,” he added.
“We’ve been able to take citizen science data and, through machine learning methodology, put it on the same footing as traditionally structured surveys, in terms of the type of signal we can find,” said Cornell science product manager Tom Auer. “It will increase the credibility and confidence of people who use this information for precise conservation all over the globe.”
The Up Side
Since 1970, North America has lost one-quarter of its breeding birds, following a global trend of declines across species. The causes range from increased pollution and land development to changing climate and decreased food resources. Efforts to reverse this loss depend on identifying the areas where birds live at highest risk, assessing their populations, and pinpointing locations where conservation could help most.
For 83% of the reported species in the new study, the decline was greatest in spots where populations had previously been most abundant — indicating problems with the habitat.
“Even in species where populations are declining a lot, there are still places of hope, where the populations are going up,” Johnston said. The team found population increases in the maps of 97% of the reported species. “That demonstrates that there’s opportunity for those species.”
“Birds face so many challenges,” said Cornell conservationist Amanda Rodewald. “This research will help us make strategic decisions about making changes that are precise, effective, and less costly. This is transformative. Now we can really drill in and know where specifically we’re going to be able to have the most positive impact in trying to stem bird declines.”
By Karen Romano Young
NASA Headquarters, Washington
Share
Details
Last Updated Jun 25, 2025 Related Terms
Earth Moderate Resolution Imaging Spectroradiometer (MODIS) Explore More
3 min read NASA Scientists Find Ties Between Earth’s Oxygen and Magnetic Field
Article
1 week ago
1 min read From Space to Soil: How NASA Sees Forests
NASA uses satellite lidar technology to study Earth’s forests, key carbon sinks.
Article
1 week ago
12 min read NASA’s Hurricane Science, Tech, Data Help American Communities
With hurricane season underway, NASA is gearing up to produce cutting-edge research to bolster the…
Article
2 weeks ago
Keep Exploring Discover More Topics From NASA
Earth
Your home. Our Mission. And the one planet that NASA studies more than any other.
Explore Earth Science
Earth Science in Action
NASA’s unique vantage point helps us inform solutions to enhance decision-making, improve livelihoods, and protect our planet.
Earth Multimedia & Galleries
View the full article
-
By NASA
2 min read
Preparations for Next Moonwalk Simulations Underway (and Underwater)
From Sunday, June 22 to Wednesday, July 2, two research aircraft will make a series of low-altitude atmospheric research flights near Philadelphia, Baltimore, and some Virginia cities, including Richmond, as well as over the Los Angeles Basin, Salton Sea, and Central Valley in California.
NASA’s P-3 Orion aircraft, based out of the agency’s Wallops Flight Facility in Virginia, along with Dynamic Aviation’s King Air B200 aircraft, will fly over parts of the East and West coasts during the agency’s Student Airborne Research Program. The science flights will be conducted between June 22 and July 2, 2025. NASA/Garon Clark Pilots will operate the aircraft at altitudes lower than typical commercial flights, executing specialized maneuvers such as vertical spirals between 1,000 and 10,000 feet, circling above power plants, landfills, and urban areas. The flights will also include occasional missed approaches at local airports and low-altitude flybys along runways to collect air samples near the surface.
The East Coast flights will be conducted between June 22 and Thursday, June 26 over Baltimore and near Philadelphia, as well as near the Virginia cities of Hampton, Hopewell, and Richmond. The California flights will occur from Sunday, June 29 to July 2.
The flights, part of NASA’s Student Airborne Research Program (SARP), will involve the agency’s Airborne Science Program’s P-3 Orion aircraft (N426NA) and a King Air B200 aircraft (N46L) owned by Dynamic Aviation and contracted by NASA. The program is an eight-week summer internship program that provides undergraduate students with hands-on experience in every aspect of a scientific campaign.
The P-3, operated out of NASA’s Wallops Flight Facility in Virginia, is a four-engine turboprop aircraft outfitted with a six-instrument science payload to support a combined 40 hours of SARP science flights on each U.S. coast. The King Air B200 will fly at the same time as the P-3 but in an independent flight profile. Students will assist in the operation of the science instruments on the aircraft to collect atmospheric data.
“The SARP flights have become mainstays of NASA’s Airborne Science Program, as they expose highly competitive STEM students to real-world data gathering within a dynamic flight environment,” said Brian Bernth, chief of flight operations at NASA Wallops.
“Despite SARP being a learning experience for both the students and mentors alike, our P-3 is being flown and performing maneuvers in some of most complex and restricted airspace in the country,” said Bernth. “Tight coordination and crew resource management is needed to ensure that these flights are executed with precision but also safely.”
For more information about Student Airborne Research Program, visit:
https://science.nasa.gov/earth-science/early-career-opportunities/student-airborne-research-program/
By Olivia Littleton
NASA’s Wallops Flight Facility, Wallops Island, Va.
Share
Details
Last Updated Jun 20, 2025 Related Terms
Airborne Science Aeronautics Wallops Flight Facility 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.