Enter Note Done
Go to previous page in this tab
Session
  • Presentation | IN13B: Large Language Models and Agentic Workflows in Science: Applications, Safety, and Geoscience Innovations II Poster
  • Poster
  • Share Icon
    Bookmark Icon
  • [ONLINE] IN13B-VR8866: AI-Powered Data Extraction, Integration and Analysis on the Geochemistry of Returned Lunar Samples
    • Schedule
    Notes
  • Online
    Online
    Set Timezone

Generic 'disconnected' Message
Author(s):
Ping Wang, University of Tennessee, Knoxville (First Author)
Dominick Pelaia, L&N STEM Academy
Zhitong Zou, Valley Christian High School
Stephen Xiao, Farragut High School
Amanda He, Valley Christian High School
Nathan He, Ocean Lakes High School
Flora Zhu, Great Neck South High School
Nathan Mao, The Harker School
Jinqi Wu, Harvard University
Yanran Chen, University of Notre Dame
Jian Wu, Old Dominion University
Meng Jiang, University of Notre Dame
Clive Neal, Univ Notre Dame
Shichun Huang, University of Tennessee (Presenting Author)


Our hands-on planet+AI curriculum development team, which includes high school students from across the nation, is developing a research-driven curriculum by taking advantage of emerging AI technologies for lunar research. With the increased interest in the Moon, especially with new sample returns, our ongoing work uses large language models (LLMs) and vision language models (VLMs) to accurately extract data from PDFs of published research on the chemical and isotopic compositions of lunar samples returned by the U.S. Apollo, the Soviet Union Luna, and Chinese Chang’E missions.



Scientific Discipline
Suggested Itineraries
Neighborhood
Type
Where to Watch
Main Session
Discussion