Jump to content

Invited Guest Speaker at the Taylor Geospatial Institutes GEOAI Gathering


Recommended Posts

  • Publishers
Posted

Manil Maskey (ST11/IMPACT) was an invited guest at the Taylor Geospatial Institute (TGI) GeoAI gathering. He presented on the Harmonized Landsat Sentinel-2 (HLS) based geospatial foundation model and the recent developments in weather and climate foundation model. Following the presentation, Maskey engaged in discussions that led to several agencies expressing interest in collaborating with IMPACT on these foundation models. TGI’s mission is to catalyze collaboration across our consortium, to connect partners in the broader geospatial ecosystem, and to align distinctive strengths, collective expertise, and shared resources to generate innovative research and solutions.

impact-logo-2.png?w=304

View the full article

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.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

  • Similar Topics

    • By NASA
      An image of a coastal marshland combines aerial and satellite views in a technique similar to hyperspectral imaging. Combining data from multiple sources gives scientists information that can support environmental management.John Moisan When it comes to making real-time decisions about unfamiliar data – say, choosing a path to hike up a mountain you’ve never scaled before – existing artificial intelligence and machine learning tech doesn’t come close to measuring up to human skill. That’s why NASA scientist John Moisan is developing an AI “eye.”
      Oceanographer John MoisanNASA Moisan, an oceanographer at NASA’s Wallops Flight Facility near Chincoteague, Virginia, said AI will direct his A-Eye, a movable sensor. After analyzing images his AI would not just find known patterns in new data, but also steer the sensor to observe and discover new features or biological processes. 
      “A truly intelligent machine needs to be able to recognize when it is faced with something truly new and worthy of further observation,” Moisan said. “Most AI applications are mapping applications trained with familiar data to recognize patterns in new data. How do you teach a machine to recognize something it doesn’t understand, stop and say ‘What was that? Let’s take a closer look.’ That’s discovery.”
      Finding and identifying new patterns in complex data is still the domain of human scientists, and how humans see plays a large part, said Goddard AI expert James MacKinnon. Scientists analyze large data sets by looking at visualizations that can help bring out relationships between different variables within the data.
      Infrared images like this one from a marsh area on the Maryland/Virginia Eastern Shore coastal barrier and back bay regions reveal clues to scientists about plant health, photosynthesis, and other conditions that affect vegetation and ecosystems.John Moisan It’s another story to train a computer to look at large data streams in real time to see those connections, MacKinnon said. Especially when looking for correlations and inter-relationships in the data that the computer hasn’t been trained to identify. 
      Moisan intends first to set his A-Eye on interpreting images from Earth’s complex aquatic and coastal regions. He expects to reach that goal this year, training the AI using observations from prior flights over the Delmarva Peninsula. Follow-up funding would help him complete the optical pointing goal.
      “How do you pick out things that matter in a scan?” Moisan asked. “I want to be able to quickly point the A-Eye at something swept up in the scan, so that from a remote area we can get whatever we need to understand the environmental scene.” 
      Moisan’s on-board AI would scan the collected data in real-time to search for significant features, then steer an optical sensor to collect more detailed data in infrared and other frequencies. 
      Thinking machines may be set to play a larger role in future exploration of our universe. Sophisticated computers taught to recognize chemical signatures that could indicate life processes, or landscape features like lava flows or craters, might offer to increase the value of science data returned from lunar or deep-space exploration. 
      Today’s state-of-the-art AI is not quite ready to make mission-critical decisions, MacKinnon said.
      “You need some way to take a perception of a scene and turn that into a decision and that’s really hard,” he said. “The scary thing, to a scientist, is to throw away data that could be valuable. An AI might prioritize what data to send first or have an algorithm that can call attention to anomalies, but at the end of the day, it’s going to be a scientist looking at that data that results in discoveries.” 
      Share
      Details
      Last Updated Feb 10, 2025 Related Terms
      Goddard Space Flight Center Artificial Intelligence (AI) Goddard Technology People of Goddard Technology Wallops Flight Facility Keep Exploring Discover More Topics From NASA
      Missions
      Humans in Space
      Climate Change
      Solar System
      View the full article
    • By NASA
      NASA’s Ames Research Center in California’s Silicon Valley, is celebrating 85 years of cutting-edge research and development in space, life sciences, supercomputing, aeronautics, and more for the benefit of humanity. Ames was founded as an aeronautical laboratory in December 1939, and has since contributed to many of NASA’s flagship missions from Apollo to Artemis. 
      NASA Ames experts are available for interviews Thursday, Dec. 19, and Friday, Dec. 20. To request an interview about the center’s legacy in space, science, technology, and aeronautics, email the Ames newsroom at: arc-dl-newsroom@mail.nasa.gov.
      NASA Ames experts include: 
      James Anderson, NASA Ames historian; Lynn Harper, lead of integrative studies in the NASA Space Portal, working to propel U.S. industry toward the development of a sustainable, scalable, and profitable non-NASA demand for services and products manufactured in the microgravity environment of low Earth orbit; Shivanjli Sharma, aerospace research engineer, working to enable advanced aviation technologies for new methods of air cargo and passenger transportation in urban, suburban, rural, and regional communities; Dave Alfano, chief of the Ames Intelligent Systems Division, working to produce ground and flight software systems and data architectures for data mining, analysis, integration, and management; integrated health management, and more for missions across the agency. Ames has established itself as a leader in the aeronautics industry, developing foundational technologies for advanced air vehicles, including air taxis and remotely piloted aircraft. On the International Space Station, Ames researchers have tested a method to develop nutrients off-Earth and on-demand. Cube-shaped robots have been delivered to the station to assist astronauts with routine duties. Ames engineers have developed and are testing a heat shield for the Orion crew capsule that will safely return astronauts home to Earth as part of the agency’s Artemis missions to the Moon.

      For more information on Ames’ history and contributions, visit:

      https://www.nasa.gov/reference/ames-history

      -end-
      Rachel Hoover
      Ames Research Center, Silicon Valley, Calif.
      650-604-4789
      rachel.l.hoover@nasa.gov




      View the full article
    • By NASA
      Media are invited to learn about a unique series of flight tests happening in Virginia in partnership between NASA and GE Aerospace that aim to help the aviation industry better understand contrails and their impact on the Earth’s climate. Contrails are the lines of clouds that can be created by high-flying aircraft, but they may have an unseen effect on the planet – trapping heat in the atmosphere.
      The media event will occur from 9 a.m.-12 p.m. on Monday, Nov. 25 at NASA’s Langley Research Center in Hampton, Virginia. NASA Langley’s G-III aircraft and mobile laboratory, as well as GE Aerospace’s 747 Flying Test Bed (FTB) will be on site. NASA project researchers and GE Aerospace’s flight crew will be available to discuss the Contrail Optical Depth Experiment (CODEX), new test methods and technologies used, and the real-world impacts of understanding and managing contrails. Media interested in attending must contact Brittny McGraw at brittny.v.mcgraw@nasa.gov no later than 12 p.m. EST, Friday, Nov. 22.
      Flights for CODEX are being conducted this week. NASA Langley’s G-III will follow GE Aerospace’s FTB in the sky and scan the aircraft wake with Light Detection and Ranging (LiDAR) technology. This will advance the use of LiDAR by NASA to generate three-dimensional imaging of contrails to better characterize how contrails form and how they behave over time.
      For more information about NASA’s work in green aviation tech, visit:
      https://www.nasa.gov/aeronautics/green-aero-tech
      -end-
      David Meade 
      Langley Research Center, Hampton, Virginia 
      757-751-2034  davidlee.t.meade@nasa.gov
      View the full article
    • By NASA
      2 min read
      Geospatial AI Foundation Model Team Receives NASA Marshall Group Achievement Award 
      Rahul Ramachandran of NASA IMPACT, left, Elizabeth Fancher of NASA IMPACT, Ankur Kumar of the University of Alabama in Huntsville (UAH), Sujit Roy of UAH, Raghu Ganti of IBM Research, David McKenzie of NASA, Muthukumaran Ramasubramanian of UAH, Iksha Gurung of UAH, and Manil Maskey of NASA IMPACT, right, accept the NASA Marshall Space Flight Center Group Achievement Award on Thursday, August 15, 2024 at NASA Marshall. NASA NASA’s science efforts aim to empower scientists with the tools to perform research into our planet and universe. To this end, a collaborative effort between NASA and IBM created an AI geospatial foundation model, which was released as an open-source application in 2024. 
      Trained on vast amounts of NASA Earth science data, the foundation model can be adapted for Earth science applications such as flood, burn scar, and cropland studies. Tailoring the model for a specific task takes far less data than the original training set, providing an easy path for researchers to perform AI-powered studies. 
      For their groundbreaking work on this project, the development team behind the foundation model has received the NASA Marshall Space Flight Center Group Achievement Award. Their success with the model showcases their commitment to advancing AI and scientific research and will inspire progress in this field for years to come.
      The team members from NASA’s Marshall Space Fight Center /IMPACT (Interagency Implementation and Advanced Concepts Team) are:
      Rahul Ramachandran  Manil Maskey  Elizabeth Fancher  The team members from the University of Alabama in Huntsville (UAH) are: 
      Sujit Roy  Ankur Kumar  Christopher Phillips  Iksha Gurung  Muthukumaran Ramasubramanian The team members from IBM are: 
      Ranjini Bangalore  Juan Bernabe-Moreno  Dario Augusto Borges Oliveira  Linsong Chu  Blair Edwards  Paolo Fraccaro  Carlos Gomes  Raghu Ganti  Adnan Hoque  Johannes Jakubik  Levente Klein  Devyani Lambhate  Gabby Nyirjesy  Naomi Simumba  Johannes Schmude  Mudhakar Srivatsa  Harini Srinivasan  Daniela Szwarcman  Rob Parkin  Kommy Weldemariam  Campbell Watson  Bianca Zadrozny  The team members from Clark University are:
      Hamed Alemohammad  Michael Cecil  Steve Li  Sam Khallaghi  Denys Godwin  Maryam Ahmadi  Fatemeh Kordi To learn more about the NASA projects improving accessible science discovery for the benefit of all, visit the Open Science at NASA page. 
      Share








      Details
      Last Updated Aug 15, 2024 Related Terms
      Open Science Explore More
      5 min read How NASA Citizen Science Fuels Future Exoplanet Research


      Article


      1 week ago
      3 min read Meet NASA Interns Shaping Future of Open Science


      Article


      3 weeks ago
      4 min read Mapping the Red Planet with the Power of Open Science


      Article


      2 months ago
      Keep Exploring Discover Related Topics
      Missions



      Humans in Space



      Climate Change



      Solar System


      View the full article
    • By NASA
      Manil Maskey (ST11/IMPACT) was an invited panelist at the United States Geospatial Intelligence Foundation (USGIF) organized GEOINT Symposium Panel titled “Geo-GPT” for Real-Time Geospatial Discovery. The panel explored the convergence of foundational artificial intelligence models beyond large language models, unveiling the potential for groundbreaking conversational “GeoGPT” capabilities that enable real-time geospatial discovery. The discussion centered on the fusion of language processing, computer vision, and spatial reasoning to enable dynamic and interactive exploration for GEOINT planning and response missions. The panel highlighted how the integration of diverse AI models can enhance the richness and accuracy of geospatial conversational AI experiences. This allows seamless interactions between humans and machines, empowering users to intuitively engage with real-time maps, interrogate them, and receive insights through natural language dialogue. Maskey shared insights on the NASA Science Mission Directorate’s (SMD’s) activities in the development and use of large language models (LLMs) and foundation models.
      The USGIF is an educational foundation dedicated to promoting the geospatial intelligence tradecraft. It aims to develop a stronger GEOINT community by bringing together government, industry, academia, professional organizations, and individuals to address national security challenges through geospatial intelligence. The recording of the panel can be found here. – https://www.youtube.com/watch?v=oHzsIe2Kfmo.

      View the full article
  • Check out these Videos

×
×
  • Create New...