AI News, Artificial intelligence analyzes gravitational lenses 10 million times faster

Artificial intelligence analyzes gravitational lenses 10 million times faster

'Analyses that typically take weeks to months to complete, that require the input of experts and that are computationally demanding, can be done by neural nets within a fraction of a second, in a fully automated way and, in principle, on a cell phone's computer chip,' said postdoctoral fellow Laurence Perreault Levasseur, a co-author of a study published today in Nature.

Lightning Fast Complex Analysis The team at the Kavli Institute for Particle Astrophysics and Cosmology (KIPAC), a joint institute of SLAC and Stanford, used neural networks to analyze images of strong gravitational lensing, where the image of a faraway galaxy is multiplied and distorted into rings and arcs by the gravity of a massive object, such as a galaxy cluster, that's closer to us.

The distortions provide important clues about how mass is distributed in space and how that distribution changes over time -- properties linked to invisible dark matter that makes up 85 percent of all matter in the universe and to dark energy that's accelerating the expansion of the universe.

Prepared for Data Floods of the Future 'The neural networks we tested -- three publicly available neural nets and one that we developed ourselves -- were able to determine the properties of each lens, including how its mass was distributed and how much it magnified the image of the background galaxy,' said the study's lead author Yashar Hezaveh, a NASA Hubble postdoctoral fellow at KIPAC.

The ability to sift through large amounts of data and perform complex analyses very quickly and in a fully automated fashion could transform astrophysics in a way that is much needed for future sky surveys that will look deeper into the universe -- and produce more data -- than ever before.

Neural networks meet space

Researchers from the Department of Energy’s SLAC National Accelerator Laboratory and Stanford University have for the first time shown that neural networks—a form of artificial intelligence—can accurately analyze the complex distortions in spacetime known as gravitational lenses 10 million times faster than traditional methods.

“Analyses that typically take weeks to months to complete, that require the input of experts and that are computationally demanding, can be done by neural nets within a fraction of a second, in a fully automated way and, in principle, on a cell phone’s computer chip,”

The team at the Kavli Institute for Particle Astrophysics and Cosmology (KIPAC), a joint institute of SLAC and Stanford, used neural networks to analyze images of strong gravitational lensing, where the image of a faraway galaxy is multiplied and distorted into rings and arcs by the gravity of a massive object, such as a galaxy cluster, that’s closer to us.

— Researchers from the Department of Energy’s SLAC National Accelerator Laboratory and Stanford University have for the first time shown that neural networks – a form of artificial intelligence – can accurately analyze the complex distortions in spacetime known as gravitational lenses 10 million times faster than traditional methods.

“Analyses that typically take weeks to months to complete, that require the input of experts and that are computationally demanding, can be done by neural nets within a fraction of a second, in a fully automated way and, in principle, on a cell phone’s computer chip,” said postdoctoral fellow Laurence Perreault Levasseur, a co-author of a study published today in Nature.

(Greg Stewart/SLAC National Accelerator Laboratory) Lightning Fast Complex Analysis The team at the Kavli Institute for Particle Astrophysics and Cosmology (KIPAC), a joint institute of SLAC and Stanford, used neural networks to analyze images of strong gravitational lensing, where the image of a faraway galaxy is multiplied and distorted into rings and arcs by the gravity of a massive object, such as a galaxy cluster, that’s closer to us.

The distortions provide important clues about how mass is distributed in space and how that distribution changes over time – properties linked to invisible dark matter that makes up 85 percent of all matter in the universe and to dark energy that’s accelerating the expansion of the universe.

(Brad Plummer/SLAC National Accelerator Laboratory) Prepared for Data Floods of the Future “The neural networks we tested – three publicly available neural nets and one that we developed ourselves – were able to determine the properties of each lens, including how its mass was distributed and how much it magnified the image of the background galaxy,” said the study’s lead author Yashar Hezaveh, a NASA Hubble postdoctoral fellow at KIPAC.

The ability to sift through large amounts of data and perform complex analyses very quickly and in a fully automated fashion could transform astrophysics in a way that is much needed for future sky surveys that will look deeper into the universe – and produce more data – than ever before.

The researchers used particular kinds of neural networks, called convolutional neural networks, in which individual computational units (neurons, gray spheres) of each layer are also organized into 2-D slabs that bundle information about the original image into larger computational units.

Brain-Like Neural Networks Study Space-Time Distortions at Breakneck Speed

The new study trained an artificial-intelligence system to examine features called gravitational lenses in images from the Hubble Space Telescope as well as simulated images.

The process could give researchers a better glimpse of how mass is distributed in the galaxy, and provide close-ups of distant galactic objects.

"Analyses that typically take weeks to months to complete, that require the input of experts and that are computationally demanding, can be done by neural nets within a fraction of a second, in a fully automated way and, in principle, on a cell phone's computer chip,"

The distorted ring of light that results, sometimes called an Einstein ring, can be analyzed to learn about both the distant system itself and the mass of the object passing in front of it.

Neural networks work by exposing an artificial-intelligence system with a particular brain-inspired architectureto millions or billions of examples of given properties, thus helping researchers learn how to identify those properties in other situations.

For instance, showing a neural network increasingly more photos of dogs would allow it to identify dogs more and more accurately, without requiring the researchers to tell the network which details to pay attention to.

For example, Google's AlphaGo program was shown a large number of Go games to analyze and process, and it ultimately defeated a world championof the complex game.

"But new algorithms combined with modern graphics processing units, or GPUs, can produce extremely fast and reliable results, as the gravitational lens problem tackled in this paper dramatically demonstrates.

New AI Analyzes Astronomical Images 10 Million Times Faster Than Humans

Researchers at SLAC National Accelerator Laboratory and Stanford University developed a neural network that can analyze images of gravitational lensing 10 million times faster than conventional techniques, which could dramatically extend the range and resolution of telescopes like Hubble and provide crucial information on galaxy clusters and dark matter.

The number of gravitational lensing images is expected to increase from only a few hundred right now to tens of thousands in a few years, so we'll need a much faster way to analyze them.

These gravitational lenses can let us peer deep into the distant universe and make out galaxies and other objects we wouldn't otherwise be able to see, but gravitational lenses can also tell us a great deal about the stars and galaxies doing the lensing.

Astronomers can tell the size and mass of a galaxy based on how strongly it curves light around it, which makes gravitational lenses perfect ways to study dark matter.

The researchers hope that their neural networks will become the go-to method for analyzing gravitational lensing, and they believe there are many more applications for using this type of algorithm in astronomy and other sciences.

AI Allows Astrophysicists To Analyze Data 10 Million Times Faster

Researchers at the Kavli Institute for Astrophysics and Cosmology have begun to use advanced artificial intelligence to analyse images of gravitational lensing, ...

AI does astronomer's job 10 million times faster

Analyzing the gravitational lensing effect can take astronomers weeks and months. Artificial intelligence can do it in seconds. Learn more about this story at ...

The Mysterious Architecture of the Universe - with J Richard Gott

J Richard Gott leads a journey through the history of our understanding of the Universe's structure, and explains the 'cosmic web': the idea that our Universe is ...

15 August 2017, “Unveiling the Dark Universe” by Dr. Yashar Hezaveh

Unveiling the Dark Universe: A Tale of Fish Tanks, Wine Glasses, and the Smallest Dark Matter Clumps” by Yashar Hezaveh, PhD., Stanford, Kavli Institute What ...