NASA, IBM team up to spur new discoveries about Earth | Tech News

NASA, IBM team up to spur new discoveries about Earth

The joint work will apply AI foundation model technology to NASA's Earth-observing satellite data for the first time, NASA said in a statement.

By:PTI
| Updated on: Feb 03 2023, 09:25 IST
Top astronomy photos of the week by NASA: Galaxy wars, Nebula, Moon to Sun, check them out
NASA
1/7 On January 14, NASA released an image of Perihelion Sun 2023, the image was taken after January 4, at the Earth's closest approach to the Sun. It was taken less than 24 hours after the earth's close approach. (Peter Ward (Barden Ridge Observatory))
image caption
2/7 On January 15, another photograph was released of The Crab Nebula snapped by the Hubble Space Telescope. The Crab Nebula, the result of a supernova seen in 1054 AD, is filled with mysterious filaments. ( NASA, ESA, Hubble, J. Hester, A. Loll (ASU))
image caption
3/7 On January 16, NASA released an image of Moon Enhanced. The featured image is a composite of multiple images enhanced to bring up real surface features. The dark areas in the image, called maria, have fewer craters and were once seas of molten lava. Additionally, the image colours, although based on the moon's real composition, are changed, and exaggerated. (Darya Kawa Mirza)
image caption
4/7 On January 17, the image of unexpected clouds toward the Andromeda Galaxy was released. (Yann Sainty & Marcel Drechsler)
image caption
5/7 Image of MACS0647: Gravitational Lensing of the Early Universe Captured by James Webb Space Telescope was released by NASA on January 18. ( NASA, ESA, CSA, Dan Coe (STScI), Rebecca Larson (UT), Yu-Yang Hsiao (JHU); Processing: Alyssa Pagan (STScI); Text: Michael Rutkowski (Minn. St. U. Mankato))
image caption
6/7 On January 19, the image of The Seagull Nebula was released. The complex of gas and dust clouds with other stars of the Canis Majoris OB1 association spans over 200 light-years. (Carlos Taylor)
image caption
7/7 Galaxy Wars: M81 and M82, this image was released on January 20. On the right, with grand spiral arms and bright yellow core is spiral galaxy M81.  (Andreas Aufschnaiter)
NASA
icon View all Images
One project will train an IBM geospatial intelligence foundation model on NASA's Harmonized Landsat Sentinel-2 (HLS) dataset. (REUTERS)

NASA and IBM have collaborated to develop artificial intelligence (AI) based models that will make it easier to mine vast datasets to advance scientific knowledge about Earth, and help the world to adapt to a changing environment.

The joint work will apply AI foundation model technology to NASA's Earth-observing satellite data for the first time, NASA said in a statement.

Foundation models are types of AI models that are trained on a broad set of unlabelled data, can be used for different tasks, and can apply information about one situation to another.

Also read
Looking for a smartphone? To check mobile finder click here.

"The beauty of foundation models is they can potentially be used for many downstream applications," said Rahul Ramachandran, a senior research scientist at NASA's Marshall Space Flight Center.

"Building these foundation models cannot be tackled by small teams; you need teams across different organisations to bring their different perspectives, resources, and skill sets," Ramachandran said in a statement.

One project will train an IBM geospatial intelligence foundation model on NASA's Harmonized Landsat Sentinel-2 (HLS) dataset, a record of land cover and land use changes captured by Earth-orbiting satellites, the statement said.

By analysing satellite data to identify changes in the geographic footprint of phenomena such as natural disasters, cyclical crop yields, and wildlife habitats, this model technology will help researchers provide critical analysis of our planet's environmental systems.

Another output from this collaboration is expected to be an easily searchable corpus of Earth science literature.

IBM has developed a natural language processing (NLP) model trained on nearly 300,000 Earth science journal articles to organise the literature and make it easier to discover new knowledge, the company said.

Beyond providing a resource to researchers, the new language model for Earth science could be infused into NASA's scientific data management and stewardship processes.

Catch all the Latest Tech News, Mobile News, Laptop News, Gaming news, Wearables News , How To News, also keep up with us on Whatsapp channel,Twitter, Facebook, Google News, and Instagram. For our latest videos, subscribe to our YouTube channel.

First Published Date: 03 Feb, 09:19 IST
Tags:
NEXT ARTICLE BEGINS