AI reveals 800 never-before-seen ‘cosmic anomalies’ in old Hubble images

Scientists analyzed more than 100 million image cutouts from a Hubble Space Telescope archive and found hundreds of previously undiscovered objects

By Jackie Flynn Mogensen edited by Claire Cameron

A composite of different anomalies discovered by Hubble — Six previously undiscovered astrophysical objects from an archive of Hubble Space Telescope data.

ESA/Hubble/NASA/D. O’Ryan/P. Gómez/European Space Agency/M. Zamani/ESA/Hubble

Join Our Community of Science Lovers!

The universe is so vast, and the difficulty of discovering all that there is out in the cosmos is so great, that one might as well count all the grains of sand in the Sahara. But now, with the help of artificial intelligence, astronomers have revealed more than 800 previously unknown “cosmic anomalies” hidden in archival data from the Hubble Space Telescope.

Researchers at the European Space Agency (ESA) developed an AI tool that sifted through nearly 100 million image cutouts in the Hubble Legacy Archive, a collection of data from as early as 35 years ago. Incredibly, the AI took just two and a half days to run through the entire archive, a task that would have taken a human research team exponentially longer to accomplish.

A small image of several galaxies with distorted shapes. The central galaxy is bluish in colour with a bright center. It is stretched out into a long, curled bar. At one end sits a reddish galaxy, which the bar curves around. — Merging galaxies from Hubble’s archive.
ESA/Hubble/NASA/D. O’Ryan/P. Gómez/European Space Agency/M. Zamani/ESA/Hubble

On supporting science journalism

If you're enjoying this article, consider supporting our award-winning journalism by subscribing. By purchasing a subscription you are helping to ensure the future of impactful stories about the discoveries and ideas shaping our world today.

The hunt turned up more than 1,300 “anomalous objects,” including galaxy mergers, jellyfish galaxies (so named for their trailing tentacles of gas) and other unusual features. Among these were scores of possible gravitational lenses—spots where a massive object, such as a galaxy, bends the light of a given source, such as another galaxy—as well as dozens of other oddball objects that defied easy explanation. Of all the found objects, some 800 had never been described before.

A small image of a mostly red galaxy. Unusually, it is ring-shaped with spots of light around the ring, a protruding arm on one side and a dark hole in the center. — A collisional ring galaxy from Hubble’s archive.
ESA/Hubble/NASA/D. O’Ryan/P. Gómez/European Space Agency/M. Zamani/ESA/Hubble

The work was published last month in the journal Astronomy & Astrophysics.

In a statement, ESA data scientist and co-author on the paper Pablo Gómez said the AI approach could offer a model for exploring other space science archives. “It [shows] how useful this tool will be for other large datasets,” he said.

Subscribe to Support Independent Journalism

Great science journalism requires human expertise, time, effort and creativity. And it costs money. That’s why I and the journalists here at Scientific American hope you’ll join our community.

When you subscribe, you are supporting staff and freelance journalists who are passionate about telling science stories that are true, important and compelling. Our editors and reporters are often experts in their fields, which means they understand the nuances of big discoveries and can untangle the breakthroughs from the hype. With a subscription, you are also supporting rigorous fact-checking to ensure the words we publish are precise and accurate. And you’re supporting original illustrations, graphics and photos that bring you closer to an advanced laboratory, an ice sheet in Antarctica or a space mission in orbit. You’re helping us craft other types of high-quality journalism as well: Our newsletters are carefully written, edited and curated by staffers you have or will come to know and love. Our Science Quickly podcast is based on original reporting, collaboration with editors and scientists and exacting production.

Subscriptions keep this engine running so we can continue to deliver thoughtful, rigorous and independent science journalism to you. In an era of viral misinformation, this work is crucial. If you value what we do, I hope you’ll consider joining us as a subscriber

Thank you,

Jeanna Bryner, Editor in Chief, Scientific American