New IBM Basis Mannequin Know-how Leverages NASA Earth Science Information for Geospatial Intelligence

YORKTOWN HEIGHTS, N.Y., Feb. 1, 2023 /PRNewswire/ — IBM (NYSE: IBM) and NASA’s Marshall House Flight Middle immediately announce a collaboration to use IBM’s synthetic intelligence (AI) expertise to uncover new insights in NASA’s huge trove of Earth and geospatial science knowledge. The joint work will apply AI basis mannequin expertise to NASA’s Earth-observing satellite tv for pc knowledge for the primary time.

Basis fashions are sorts of AI fashions which can be skilled on a broad set of unlabeled knowledge, can be utilized for various duties, and can apply details about one state of affairs to one other. These fashions have quickly superior the sector of pure language processing (NLP) expertise over the past 5 years, and IBM is pioneering purposes of basis fashions past language.

Earth observations that enable scientists to research and monitor our planet are being gathered at unprecedented charges and quantity. New and progressive approaches are required to extract data from these huge knowledge sources. The aim of this work is to present a neater manner for researchers to analyze and draw insights from these massive datasets. IBM’s basis mannequin expertise has the potential to velocity up the invention and evaluation of these knowledge so as to shortly advance the scientific understanding of Earth and response to climate-related points. 

IBM and NASA plan to develop a number of new applied sciences to extract insights from Earth observations. One venture will practice an IBM geospatial intelligence basis mannequin on NASA’s Harmonized Landsat Sentinel-2 (HLS) dataset, a report of land cowl and land use modifications captured by Earth-orbiting satellites. By analyzing petabytes of satellite tv for pc knowledge to establish modifications within the geographic footprint of phenomena resembling pure disasters, cyclical crop yields, and wildlife habitats, this basis mannequin expertise will assist researchers present essential evaluation of our planet’s environmental techniques.

One other output from this collaboration is anticipated to be an simply searchable corpus of Earth science literature. IBM has developed an NLP mannequin skilled on practically 300,000 Earth science journal articles to manage the literature and make it simpler to uncover new data. Containing one of the most important AI workloads skilled on Purple Hat’s OpenShift software program to date, the totally skilled mannequin makes use of PrimeQA, IBM’s open-source multilingual question-answering system. Past offering a useful resource to researchers, the brand new language mannequin for Earth science could possibly be infused into NASA’s scientific knowledge administration and stewardship processes.

“The beauty of foundation models is they can potentially be used for many downstream applications,” stated Rahul Ramachandran, senior analysis scientist at NASA’s Marshall House Flight Middle in Huntsville, Alabama. “Building these foundation models cannot be tackled by small teams,” he added. “You need teams across different organizations to bring their different perspectives, resources, and skill sets.” 

“Foundation models have proven successful in natural language processing, and it’s time to expand that to new domains and modalities important for business and society,” stated Raghu Ganti, principal researcher at IBM. “Applying foundation models to geospatial, event-sequence, time-series, and other non-language factors within Earth science data could make enormously valuable insights and information suddenly available to a much wider group of researchers, businesses, and citizens. Ultimately, it could facilitate a larger number of people working on some of our most pressing climate issues.”

Different potential IBM-NASA joint initiatives on this settlement embrace setting up a basis mannequin for climate and local weather prediction utilizing MERRA-2, a dataset of atmospheric observations. This collaboration is a component of NASA’s Open-Supply Science Initiative, a dedication to constructing an inclusive, clear, and collaborative open science group over the following decade.

For extra details about this collaboration, go to the IBM Research Weblog.

Statements concerning IBM’s future course and intent are topic to change or withdrawal with out discover, and signify objectives and aims solely.

Press contact
Bethany Hill McCarthy
IBM Research
[email protected]


What's Your Reaction?

hate hate
confused confused
fail fail
fun fun
geeky geeky
love love
lol lol
omg omg
win win
The Obsessed Guy
Hi, I'm The Obsessed Guy and I am passionate about artificial intelligence. I have spent years studying and working in the field, and I am fascinated by the potential of machine learning, deep learning, and natural language processing. I love exploring how these technologies are being used to solve real-world problems and am always eager to learn more. In my spare time, you can find me tinkering with neural networks and reading about the latest AI research.


Your email address will not be published. Required fields are marked *