A team of astronomers have used a new AI-assisted method to search for rare astronomical objects in the Hubble Legacy Archive. The team sifted through nearly 100 million image cutouts in just two and a half days, uncovering nearly 1400 anomalous objects, more than 800 of which had never been documented before.
Rare and anomalous objects like colliding galaxies, gravitational lenses and ring galaxies are of immense scientific interest, but they’re difficult to find in the growing masses of data from telescopes like the Hubble Space Telescope. Increasingly, astronomers must ask how they can find a cosmic needle in a haystack the size of the Universe.
Recently, researchers David O’Ryan and Pablo Gómez of the European Space Agency developed an AI tool that allows them to inspect millions of astronomical images in a fraction of the time it would take a human. The team trained their tool and demonstrated its capabilities using the Hubble Legacy Archive, which contains tens of thousands of datasets spanning Hubble’s long lifetime.
“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,” says David O’Ryan, lead author of the research paper published in the journal Astronomy & Astrophysics.
Astrophysical anomalies are usually discovered when scientists manually search for objects that are outside the norm — or find them by chance. While trained scientists excel at spotting cosmic anomalies, there’s simply too much Hubble data for experts to sort through at the necessary level of fine detail by hand.
Citizen science projects, which enlist non-scientists to collaborate on tasks such as classifying galaxies, provide another way to chip away at the mountains of data available. While citizen science groups greatly expand the amount of data that can be inspected, they’re still no match for extensive archives like Hubble’s, or for datasets from telescopes that survey the sky like ESA’s Euclid space telescope.
Now, this new work by O’Ryan and Gómez takes the search to a whole new level. The team developed what’s called a neural network, an AI tool that uses computers to process data and search for patterns in a way that is inspired by the human brain. Their neural network, which they named AnomalyMatch, is trained to search for and recognise rare objects like jellyfish galaxies and gravitational arcs.
The team used AnomalyMatch to search through nearly 100 million image cutouts from the Hubble Legacy Archive, marking the first time the archive has been systematically searched for astrophysical anomalies. In just two and a half days, AnomalyMatch completed its search of the archive and returned a list of likely anomalies.
As the process of tracking down rare objects still requires an expert eye, O’Ryan and Gómez personally inspected the sources rated by their algorithm as most likely to be anomalous. Of these, more than 1300 were true anomalies, more than 800 of which had never been documented in the scientific literature.
Most of the anomalies were galaxies in the process of merging or interacting, taking on unusual shapes or trailing long tails of stars and gas. Many others were gravitational lenses, in which the gravity of a foreground galaxy bends spacetime and warps the light from a distant background galaxy into a circle or arc. The team also discovered examples of several other rare objects such as galaxies with huge clumps of stars, jellyfish galaxies with gaseous ‘tentacles’, and planet-forming disks seen edge-on, giving them a hamburger-like or butterfly-like appearance. Perhaps most intriguing of all, there were several dozen objects that defied classification altogether.
“This is a fantastic use of AI to maximise the scientific output of the Hubble archive,” says study co-author 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.”
Hubble has generated just one of many large data archives in astronomy, and more are on the horizon. New facilities that will return an enormous amount of data include Euclid, which began its survey of billions of galaxies across a third of the night sky in 2023, the NSF–DOE Vera C. Rubin Observatory, which will soon begin its 10-year Legacy Survey of Space and Time and collect more than 50 petabytes of images, and NASA's Nancy Grace Roman Space Telescope, to which ESA contributes as a Mission of Opportunity, that is scheduled to launch no later than May 2027. AI tools like AnomalyMatch can help astronomers handle the deluge of incoming data and discover new examples of rare and unusual objects — and maybe even things never seen before in the Universe.
Astrophysical anomalies from Hubble’s archive
Six previously-undiscovered, weird and fascinating astrophysical objects are displayed in this new image from the NASA/ESA Hubble Space Telescope. These were discovered by researchers from the European Space Agency using a new AI-assisted method. The AI tool allowed them to search nearly 100 million image cutouts and uncover anomalous objects including gravitational lenses, jellyfish galaxies with gaseous ‘tentacles’, merging and interacting galaxies, galaxies featuring rings and arcs and more.
This collection features six galaxies, showing a cross-section of the discoveries with some of the more striking examples: three lenses with arcs distorted by gravity, one galactic merger, one ring galaxy, and one galaxy — not alone in the results — which defied classification.
To detect anomalous objects like these six, the researchers developed an AI tool capable of searching and recognising patterns in images, and trained it with examples of types of unusual objects that they wanted to find. They then used their algorithm to examine the entire set of data from Hubble’s archive in search of further anomalous objects, over the course of just a couple of days. The result was a ranking of which images contained objects most likely to be anomalous.
After inspecting the results from their AI tool, the team confirmed almost 1400 anomalies, of which over 800 were previously unknown. With even larger datasets on the way from missions including ESA’s Euclid, the hope is that AI tools such as this one can help astronomers to make the absolute most of their observations.
Read more about this new research here.
[Image description: A collage of six images, showing different kinds of “anomalous” astrophysical objects. These are galaxies with unusual shapes, among them a ring-shaped galaxy, a bipolar galaxy, a group of merging galaxies, and three galaxies with warped arcs created by gravitational lensing.]
Credit:
ESA/Hubble & NASA, D. O’Ryan, P. Gómez (European Space Agency), M. Zamani (ESA/Hubble)
An anomaly from Hubble’s archive — Collisional ring galaxy
This is a previously-undiscovered astrophysical anomaly, found in the Hubble Space Telescope’s archive by researchers using a new AI-assisted method. The AI tool allowed them to sift through nearly 100 million image cutouts in just days, turning up rare and anomalous objects like this one.
This object was classified by the research team as a “collisional ring” galaxy — one of only two that were found. These are galaxies which are partly or wholly ring-shaped, but with a disrupted or bent disc that is noticeably luminous. These ring formations arise when a galaxy collides with another by crashing right through its centre, creating a roiling, circular wave of star formation. Hubble has featured other collisional ring galaxies before, but the precise alignment between colliding galaxies needed to create them means they are quite rare, including in AI-assisted searches. This galaxy was not previously recorded.
Read more about this new research here.
[Image description: 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 centre.]
Credit:
ESA/Hubble & NASA, D. O’Ryan, P. Gómez (European Space Agency), M. Zamani (ESA/Hubble)
An anomaly from Hubble’s archive — Merging galaxies 1
This is a previously-undiscovered astrophysical anomaly, found in the Hubble Space Telescope’s archive by researchers using a new AI-assisted method. The AI tool allowed them to sift through nearly 100 million image cutouts in just days, turning up rare and anomalous objects like this one.
This oval-shaped galaxy is perhaps most striking for the long, thin beam of light stretching across its centre. This is thought to be the result of a galaxy merger. A less conspicuous feature is the small arc of light just below the galaxy’s core. This is thought to be the secondary galaxy in the merger, or a potential image formed by gravitational lensing, where the mass of the foreground galaxy has bent light from a distant galaxy behind it to create the small arc of light.
Read more about this new research here.
[Image description: A small image of an elliptical galaxy. It is bright in the centre and a beam of light crosses it on the long axis. The rest of the galaxy is lit by the pale gold glow from the centre. Below the centre sits a small arc of light with a bright spot on it.]
Credit:
ESA/Hubble & NASA, D. O’Ryan, P. Gómez (European Space Agency), M. Zamani (ESA/Hubble)
An anomaly from Hubble’s archive — Merging galaxies 2
This is a previously-undiscovered astrophysical anomaly, found in the Hubble Space Telescope’s archive by researchers using a new AI-assisted method. The AI tool allowed them to sift through nearly 100 million image cutouts in just days, turning up rare and anomalous objects like this one.
A small collection of gravitationally interacting galaxies has been found here. Galaxy mergers are relatively common — they were the most abundant type of anomaly found by the researchers — and are easily identified by the distorted shapes of the galaxies’ discs and the tidal tails stretching out between them, caused by the massive gravitational forces slowly pulling each galaxy apart. Eventually the galaxies we see here will be totally disrupted and finally settle into the shape of a single galaxy, most likely an elliptical galaxy.
Read more about this new research here.
[Image description: A small image of several galaxies with distorted shapes. The central galaxy is bluish in colour with a bright centre. It is stretched out into a long, curled bar. At one end sits a reddish galaxy which the bar curves around.]
Credit:
ESA/Hubble & NASA, D. O’Ryan, P. Gómez (European Space Agency), M. Zamani (ESA/Hubble)
An anomaly from Hubble’s archive — Unknown object
This is a previously-undiscovered astrophysical anomaly, found in the Hubble Space Telescope’s archive by researchers using a new AI-assisted method. The AI tool allowed them to sift through nearly 100 million image cutouts in just days, turning up rare and anomalous objects like this one.
The strange, bi-polar galaxy seen here is certainly anomalous, with its compact, swirling core and two open lobes at the sides. Exactly what kind of galaxy it is is unclear, and it was not previously known to astronomers. It’s an example of the kinds of new and unusual finds that can be made by AI-assisted data processing, even from well-known datasets.
Read more about this new research here.
[Image description: A small image of a galaxy. Its centre is a small disc containing blotches of light. Two arcs of light come out from the top, one curving around to the left and the other to the right, both then rejoining the galaxy at the bottom creating a lobe on each side. Light from some other object just enters the frame at the top-right.]
Credit:
ESA/Hubble & NASA, D. O’Ryan, P. Gómez (European Space Agency), M. Zamani (ESA/Hubble)
An anomaly from Hubble’s archive — Gravitational lens 1
This is a previously-undiscovered astrophysical anomaly, found in the Hubble Space Telescope’s archive by researchers using a new AI-assisted method. The AI tool allowed them to sift through nearly 100 million image cutouts in just days, turning up rare and anomalous objects like this one.
This image depicts a gravitational lens, where the enormous mass of one galaxy distorts, bends and magnifies light from another galaxy behind it, resulting in a warped image of the background galaxy. The gravitational lens is easily identifiable here, with the lensed galaxy forming an arc around the dense core of the foreground, lensing galaxy.
Read more about this new research here.
[Image description: A small image of a galaxy. It’s round with a bright white centre and a faint halo of light around that. A band of light runs down through the galaxy, notably bending around the galaxy’s core as if pushed away. This band is an image of a background galaxy, formed by gravitational lensing.]
Credit:
ESA/Hubble & NASA, D. O’Ryan, P. Gómez (European Space Agency), M. Zamani (ESA/Hubble)
An anomaly from Hubble’s archive — Gravitational lens 2
This is a previously-undiscovered astrophysical anomaly, found in the Hubble Space Telescope’s archive by researchers using a new AI-assisted method. The AI tool allowed them to sift through nearly 100 million image cutouts in just days, turning up rare and anomalous objects like this one.
Two dramatically different galaxies are revealed in this Hubble image. A compact, reddish elliptical galaxy is accompanied by a blue spiral galaxy squashed into an arc shape. This is the result of gravitational lensing, where light from the spiral galaxy — actually residing in the background — has been bent by the mass of the heavy elliptical galaxy, creating this distorted image of the spiral.
Read more about this new research here.
[Image description: A small image of a galaxy. It is compact and oval-shaped, dark orange in colour with a white spot at the very centre. Along the right edge of this galaxy sits a bright blue arc, the same length as the elliptical galaxy. This is an image of a background galaxy, formed by gravitational lensing.]
Credit:
ESA/Hubble & NASA, D. O’Ryan, P. Gómez (European Space Agency), M. Zamani (ESA/Hubble)
VIDEO
Space Sparks Episode 22: Researchers discover hundreds of cosmic anomalies
This Space Sparks episode highlights how a team of astronomers have used a new AI-assisted method to search for rare astronomical objects in the Hubble Legacy Archive.
Credit:
Directed by: Bethany Downer and Nico Bartmann
Editing: Nico Bartmann
Web and technical support: Enciso Systems
Written by: Bethany Downer
Music: Stellardrone - Ascent
Footage and photos: ESA/Hubble & NASA, D. O’Ryan, P. Gómez (European Space Agency), M. Zamani (ESA/Hubble), N. Bartmann (ESA/Hubble)
Pan video: New astronomical objects
Six previously-undiscovered, weird and fascinating astrophysical objects are highlighted in this video, which showcases images from the NASA/ESA Hubble Space Telescope. These were discovered by researchers from the European Space Agency using a new AI-assisted method. The AI tool allowed them to search nearly 100 million image cutouts and uncover anomalous objects including gravitational lenses, jellyfish galaxies with gaseous ‘tentacles’, merging and interacting galaxies, galaxies featuring rings and arcs and more.
This collection features six galaxies, showing a cross-section of the discoveries with some of the more striking examples: three lenses with arcs distorted by gravity, one galactic merger, one ring galaxy, and one galaxy — not alone in the results — which defied classification. To detect anomalous objects like these six, the researchers developed an AI tool capable of searching and recognising patterns in images, and trained it with examples of types of unusual objects that they wanted to find. They then used their algorithm to examine the entire set of data from Hubble’s archive in search of further anomalous objects, over the course of just a couple of days. The result was a ranking of which images contained objects most likely to be anomalous. After inspecting the results from their AI tool, the team confirmed almost 1400 anomalies, of which over 800 were previously unknown. With even larger datasets on the way from missions including ESA’s Euclid, the hope is that AI tools such as this one can help astronomers to make the absolute most of their observations.
Credit:
NASA & ESA, N. Bartmann (ESA/Hubble)
Music: STAN DART - Organic Life
Fuente: ESA/Hubble Information Centre
Comentarios