Artificial intelligence could help us see farther into space than ever before

neural network space telescope hubble2
NASA/ESA
Distortions in space-time sound like they’d be more of a concern on an episode of Star Trek than they would in the real world. However, that’s not necessarily true: analyzing images of gravitational waves could help enormously extend both the range and resolution of telescopes like Hubble, and allow us to see farther into the universe than has been possible before.

The good news? Applying an artificial intelligence neural network to this problem turns out to accelerate its solution well beyond previous methods — like 10 million times faster. That means that analysis which could take human experts weeks or even months to complete can now be carried out by neural nets in a fraction of a single second.

Developed by researchers at Stanford University and the SLAC National Accelerator Laboratory, the new neural network is able to analyze images of so-called “gravitational lensing.” This is an effect first hypothesized about by Albert Einstein, who suggested that giant masses such as stars have the effect of curving light around them. This effect is similar to a telescope in that it allows us to examine distant objects with more clarity. However, unlike a telescope, gravitational lenses distort objects into smeared rings and arcs — so making sense of them requires the calculating abilities of a computer.

To train their network, researchers on the project showed it around half a million simulated images of gravitational lenses. After this was done, the neural net was able to spot new lenses and determine their properties — down to how their mass was distributed, and how great the magnification levels of the background galaxy were.

Given that projects like the Large Synoptic Survey Telescope (LSST), a 3.2-gigapixel camera currently under construction at SLAC, is expected to increase the number of known strong gravitational lenses from a few hundred to tens of thousands, this work comes at the perfect time.

“We won’t have enough people to analyze all these data in a timely manner with the traditional methods,” said postdoctoral fellow Laurence Perreault Levasseur, a co-author on the associated Nature research paper. “Neural networks will help us identify interesting objects and analyze them quickly. This will give us more time to ask the right questions about the universe.”

Impressively, the neural network doesn’t even need a supercomputer to run on: one of the tested neural nets was designed to work on an iPhone. Studying the universe in greater detail than ever? Turns out there’s an app for that!

Emerging Tech

Awesome Tech You Can’t Buy Yet: Booze-filled ski poles and crypto piggy banks

Check out our roundup of the best new crowdfunding projects and product announcements that hit the web this week. You may not be able to buy this stuff yet, but it sure is fun to gawk!
Emerging Tech

New adhesive tech could let you remove Band-Aids with a blast of UV light

Pulling off Band-Aids sucks. But that could be about to change, thanks to a new type of adhesive that can be easily detached using a specific frequency of UV light. Here's how it works.
Emerging Tech

‘Crop duster’ robot is helping reseed the Great Barrier Reef with coral

In a world first, an undersea robot has delivered microscopic coral larvae to the Great Barrier Reef. Meet Larvalbot: the robot "crop duster" which dispenses coral babies on troubled reefs.
Computing

Nvidia’s Jetson AGX Xavier module is designed to give robots better brains

Nvidia's pricey Jetson AGX Xavier might help drive the next generation of smart robots. Nvidia hopes that developers will use its new Xavier module to power AI-driven machines like delivery drones and robots used in manufacturing.
Movies & TV

Pedro Pascal officially cast as 'The Mandalorian' as Disney show fills out cast

The Mandalorian, Jon Favreau's live-action Star Wars series planned for Disney's streaming video service, will be one of the most expensive television shows ever made. Here's everything we know about it so far.
Emerging Tech

Bright ‘hyperactive’ comet should be visible in the sky this weekend

An unusual green comet, 46P/Wirtanen, will be visible in the night sky this month as it makes its closest approach to Earth in 20 years. It may even be possible to see the comet without a telescope.
Emerging Tech

Meet the MIT scientist who’s growing semi-sentient cyborg houseplants

Elowan is a cybernetic plant that can respond to its surroundings. Tethered by a few wires and silver electrodes, the plant-robot hybrid can move in response to bioelectrochemical signals that reflect the plant’s light demands.
Emerging Tech

Gorgeous images show storms and cloud formations in the atmosphere of Jupiter

NASA's Juno mission arrived at Jupiter in 2016 and has been collecting data since then. NASA has shared an update on the progress of the mission as it reaches its halfway point, releasing stunning images of the planet as seen from orbit.
Emerging Tech

Beautiful image of young planets sheds new light on planet formation

Researchers examining protoplanetary disks -- the belts of dust that eventually form planets -- have shared fascinating images of the planets from their survey, showing the various stages of planet formation.
Emerging Tech

Delivery robot goes up in flames while out and about in California

A small meal-delivery robot suddenly caught fire in Berkeley, California, on Friday. The blaze was quickly tackled and no one was hurt, but the incident is nevertheless a troubling one for the fledgling robot delivery industry.
Emerging Tech

High-tech dancing robot turns out to be a guy in a costume

A Russian TV audience was impressed recently by an adult-sized "robot" that could dance and talk. But when some people began pointing out that its actions were a bit odd, the truth emerged ... it was a fella in a robot suit.
Emerging Tech

MIT’s smart capsule could be used to release drugs in response to a fever

Researchers have developed a 3D-printed capsule which can monitor patients' vital signs, transmit this information to a connected device, and release drugs in response to symptoms.
Emerging Tech

Self-driving dirt rally vehicle offers crash course in autonomous car safety

Georgia Tech's AutoRally initiative pushes self-driving cars to their limit by getting scaled-down autonomous vehicles to drive really, really fast and aggressively on dirt roads. Here's why.
Features

Cities looking to get smart take a lesson from an iconic shopping mall

From Disney World to the Mall of America, public venues are becoming microcosms for smart city projects. We dove into both, to show what government officials can learn – and what you can expect from your city.