Skip to main content
  1. Home
  2. Space
  3. News

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

Luke Dormehl
By

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.

Recommended Videos

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!

Topics
Luke Dormehl
Luke Dormehl
Contributor
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Biggest stellar black hole to date discovered in our galaxy
Astronomers have found the most massive stellar black hole in our galaxy, thanks to the wobbling motion it induces on a companion star. This artist’s impression shows the orbits of both the star and the black hole, dubbed Gaia BH3, around their common centre of mass. This wobbling was measured over several years with the European Space Agency’s Gaia mission. Additional data from other telescopes, including ESO’s Very Large Telescope in Chile, confirmed that the mass of this black hole is 33 times that of our Sun. The chemical composition of the companion star suggests that the black hole was formed after the collapse of a massive star with very few heavy elements, or metals, as predicted by theory.

Black holes generally come in two sizes: big and really big. As they are so dense, they are measured in terms of mass rather than size, and astronomers call these two groups of stellar mass black holes (as in, equivalent to the mass of the sun) and supermassive black holes. Why there are hardly any intermediate-mass black holes is an ongoing question in astronomy research, and the most massive stellar mass black holes known in our galaxy tend to be up to 20 times the mass of the sun. Recently, though, astronomers have discovered a much larger stellar mass black hole that weighs 33 times the mass of the sun.

Not only is this new discovery the most massive stellar black hole discovered in our galaxy to date but it is also surprisingly close to us. Located just 2,000 light-years away, it is one of the closest known black holes to Earth.

Read more
Watch how NASA plans to land a car-sized drone on Titan
An artist's impression of NASA's Dragonfly drone.

 

A decision by NASA this week paved the way for the Dragonfly drone mission to continue to completion.

Read more
See a flyby of Io, a hellish moon with lakes of lava and an otherworldly mountain
The JunoCam instrument on NASA’s Juno captured this view of Jupiter’s moon Io — with the first-ever image of its south polar region — during the spacecraft’s 60th flyby of Jupiter on April 9.

NASA's Juno mission is best known for the gorgeous images of Jupiter that it has taken since its launch in 2011 and arrival at Jupiter in 2016. But the spacecraft hasn't only investigated the planet -- it has also studied Jupiter's many moons, like the large Ganymede and the icy Europa. Recently, the spacecraft has been making close flybys of the Jovian moon Io, which is the most volcanically active body in the solar system. And it has observed some dramatic features there, like a lake of lava and a large mountain.

Even though Jupiter (and Io) are both far from the sun, and therefore receive little heat from sunlight, Io still has high internal temperatures. That's because Jupiter is so large that its gravitational pull acts on Io and creates friction, heating it up in a process called tidal heating. Though the surface of the moon is cold, at below minus 200 degrees Fahrenheit (minus 130 degrees Celsius), the volcanoes spewing out material from the planet's hot interior can reach temperatures of thousands of degrees Fahrenheit.

Read more