10 Sources
[1]
AI reveals 800 never-before-seen 'cosmic anomalies' in old Hubble images
I agree my information will be processed in accordance with the Scientific American and Springer Nature Limited Privacy Policy. We leverage third party services to both verify and deliver email. By providing your email address, you also consent to having the email address shared with third parties
[2]
Scientists let AI loose on Hubble's archives
A pair of astronomers at the European Space Agency (ESA) discovered more than 800 previously undocumented "astrophysical anomalies" hiding in Hubble's archives. To do so, researchers David O'Ryan and Pablo Gómez trained an AI model to comb through Hubble's 35-year dataset, hunting for strange
[3]
AI finds hundreds of never-before-seen 'cosmic anomalies' in old Hubble Telescope images
(Image credit: ESA/Hubble & NASA, D. O'Ryan, P. Gómez (European Space Agency), M. Zamani (ESA/Hubble)) The Hubble Space Telescope takes a lot of pictures. In fact, NASA estimates Hubble has snapped 1.7 million images since it launched in 1990. But this poses a unique issue: It's almost impossible
[4]
AI tool reveals hundreds of 'anomalies' in Hubble telescope archives -- and some defy classification
Six of the hundreds of 'anomalies' discovered in the Hubble telescope archives, including three unusual galaxies and three gravitationally lensed objects. (Image credit: ESA/Hubble & NASA, D. O'Ryan, P. Gómez (European Space Agency), M. Zamani (ESA/Hubble)) An artificial intelligence (AI) tool has
[5]
Astronomers discover over 800 cosmic anomalies using a new AI tool
Here's a use of AI that appears to do more good than harm. A pair of astronomers at the European Space Agency (ESA) developed a neural network that searches through space images for anomalies. The results were far beyond what human experts could have done. In two and a half days, it sifted through
[6]
AI Sifts Through a Mountain of Hubble Data, Uncovers Hundreds of Cosmic Weirdos
The universe is filled with innumerable astrophysical objects, each one different from the last. But even amid this vast diversity, some stand out as truly bizarre. A pair of astronomers recently discovered hundreds of these cosmic weirdos buried in archival Hubble Space Telescope data. These
[7]
Six strange galaxies found hiding in Hubble's vast archive
Today's Image of the Day from the European Space Agency shows six strange galaxies that look nothing like the calm, orderly spirals many people picture when they hear the word "galaxy." Bent arcs of light, smeared shapes, broken rings, and objects that resist easy labels all appear in one frame.
[8]
AI Discovers Hundreds of Anomalies in Archive of Hubble Images
"This is a powerful demonstration of how AI can enhance the scientific return of archival datasets." The universe is unfathomably vast, and for the astronomers trying to understand it, that means having to gather a commensurately mind-boggling amount of data. Wouldn't it be nice if there was
[9]
AI Unlocks Hundreds of Cosmic Anomalies in Hubble Archive | Newswise
Six previously undiscovered, weird and fascinating astrophysical objects are displayed in this new image from NASA's Hubble Space Telescope. They include three lenses with arcs distorted by gravity, one galactic merger, one ring galaxy, and one galaxy that defied classification. Newswise -- A team
[10]
AI Identifies More Than 1,300 Unusual Objects in Hubble Space Telescope Images
Discoveries include lenses, mergers, and jellyfish galaxies AI has analysed decades of images from the Hubble Space Telescope and found unusual celestial objects that had gone unnoticed by astronomers. ESA scientists employed a neural network called AnomalyMatch to search 100 million image cutouts
Share
Copy Link
Researchers at the European Space Agency developed an AI tool called AnomalyMatch that scanned 35 years of Hubble Space Telescope data in just two and a half days. The neural network discovered more than 1,300 cosmic anomalies, including 800 never-before-documented objects. Among them were galaxy mergers, gravitational lenses, and dozens of objects that defy existing classification schemes entirely.
Researchers at the European Space Agency (ESA) have deployed an AI tool that uncovered more than 800 previously unknown cosmic anomalies hidden within the Hubble Space Telescope archives
1
. The neural network, called AnomalyMatch AI tool, scanned nearly 100 million image cutouts from the Hubble Legacy Archive in just two and a half days—a task that would have taken human research teams exponentially longer to complete2
. This marks the first systematic search for astrophysical anomalies across the entire archive, which spans 35 years of deep space observations since the Hubble Space Telescope launched in 19903
.
Source: Futurism
Developed by ESA research fellows David O'Ryan and Pablo Gómez, AnomalyMatch uses pattern recognition to analyze images in a way similar to how our brains process visual information
3
. The findings, published in the journal Astronomy & Astrophysics, revealed nearly 1,400 anomalous objects in total, with more than 800 having never been documented before5
.The scientific discovery includes a diverse array of unusual phenomena. Most of the cosmic anomalies were galaxy mergers or interacting galaxies, which exhibit unusual shapes or trailing, elongated streams of stars and gas
4
. The AI also identified numerous gravitational lenses—spots where the gravity of a foreground galaxy bends spacetime and warps light from a background galaxy into arcs or rings1
.
Source: Scientific American
Other discoveries included jellyfish galaxies with dangling gaseous tentacles, galaxies with massive star-forming clumps, and edge-on planet-forming disks resembling hamburgers
4
. Perhaps most intriguing, several dozen objects constitute unclassifiable phenomena that defied existing classification schemes entirely2
. Each of the image cutouts examined was only a few dozen pixels per side, representing a narrow slice of sky barely a thousandth of a degree wide4
.The challenge facing astronomers is clear: NASA estimates the Hubble Space Telescope has snapped 1.7 million images since launch, creating the largest volume of observational data in astronomy history
3
. "While expert astronomers excel at identifying unusual features, the sheer volume of Hubble data makes comprehensive manual review impractical," NASA officials explained4
. Even citizen science initiatives fall short when faced with archives as extensive as Hubble's."This is a fantastic use of AI to maximize the scientific output of the Hubble archive," said Pablo Gómez. "Finding so many anomalous objects in Hubble data, where you might expect many to have already been found, is a great result. It also shows how useful this tool will be for other large datasets"
2
. ESA data scientist Gómez emphasized that the AI approach could offer a model for exploring other space science archives and vast scientific datasets1
.Related Stories
The success of AnomalyMatch points toward broader applications in data analysis for upcoming missions. Potential targets include datasets from the Euclid telescope, which is surveying billions of galaxies to create the largest 3D map of the universe, as well as the forthcoming Nancy Grace Roman Telescope and the Vera C. Rubin Observatory
4
. These instruments will hunt for exoplanets and moving objects across vast stretches of the night sky, generating a data deluge that could overwhelm traditional analysis methods."Archival observations from the Hubble Space Telescope now stretch back 35 years, providing a treasure trove of data in which astrophysical anomalies might be found," said David O'Ryan, lead author of the research paper
3
. The discovery of so many previously undocumented anomalies underscores the tool's potential for future surveys, potentially allowing faster identification of new objects than ever before. As telescopes continue generating unprecedented volumes of observational data, AI tools trained on pattern recognition may become essential for unlocking discoveries hiding in plain sight within existing archives.Summarized by
Navi
[1]
[2]
[4]
23 Apr 2026•Science and Research

17 Nov 2025•Science and Research

21 Mar 2025•Science and Research

1
Policy and Regulation

2
Technology

3
Technology
