[NASA] Help Refine Data from Space Telescopes with Artifact InSPECtor

[SpaceMan 0]

Explore This Section

1. This is the hidden content, please

   • Sign In
   • or
   • Sign Up
2. This is the hidden content, please

   • Sign In
   • or
   • Sign Up
3. Help Refine Data from Space…

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• This is the hidden content, please

  • Sign In
  • or
  • Sign Up

 

How do scientists studying space with data from a telescope hundreds of thousands of miles away know that what they are seeing is real? A new NASA project,

This is the hidden content, please

• Sign In
• or
• Sign Up

, invites you to find out – and by doing so, to help missions like

This is the hidden content, please

• Sign In
• or
• Sign Up

and NASA’s new

This is the hidden content, please

• Sign In
• or
• Sign Up

answer fundamental questions about our universe.

“It’s really cool that we can help teach computers new skills,” said nine-year-old Maeve F. after trying out Artifact InSPECtor. Participants of all ages, including those as young as Maeve, can visit the project to learn how they can contribute to science by training artificial intelligence to remove errors in telescope data.

Here’s how it works.

The Euclid space telescope, a powerful observatory built by ESA (European Space Agency) with critical contributions from NASA, is collecting light from millions of distant galaxies across the universe. It will soon be joined by NASA’s Nancy Grace Roman Space Telescope, a complementary observatory that will capture a similar number of galaxies after it begins science operations, but at different distances and densities across the sky. Together, these telescopes promise to help scientists answer questions about the expansion of the universe and dark energy – the mysterious force causing this expansion.

To collect data to answer these questions, each telescope uses a special instrument called a spectrograph that works like a prism: it splits the light from each galaxy, even very distant ones, into a rainbow of colors. By studying these rainbow patterns, called spectra, scientists can figure out how far away each galaxy is, what kinds of stars it contains, and even information about the supermassive ****** holes at their centers.

But before that can happen, there’s a problem to solve.

Telescope data contains many “artifacts” – the general name scientists use for signals that come from things other than real astronomical objects like galaxies or stars. Artifacts can be created by light glinting off the telescope’s housing, cosmic rays striking the detector, quirks in the camera or electronics, or other sources. It’s a bit like when a smudge on your phone’s camera lens shows up in a photo, or when a glare from the Sun blocks part of your picture.

To find and remove these artifacts, astronomers have created artificial intelligence (AI) tools that learn to recognize them, similar to how your phone recognizes faces in photos. But recognizing artifacts in data from relatively new instruments is challenging work for the AI, which doesn’t always distinguish them accurately

That’s where you come in! As a volunteer with Artifact InSPECtor, you’ll look at real space telescope data from Euclid and, starting in early 2027, the Nancy Grace Roman Space Telescope. The project will teach you how to recognize artifacts in data from these telescopes. The work you do will then be used to improve the instructions guiding the AI tool. Working together, you, the AI, the scientists, and these powerful space telescopes will learn more than ever before about how our universe works.

If you want to teach computers new skills and help discover the mysteries of dark energy, use your smartphone, tablet, or computer to visit Artifact InSPECtor and begin today:

This is the hidden content, please

• Sign In
• or
• Sign Up

.

This is the hidden content, please

• Sign In
• or
• Sign Up

Examples of what artifacts can look like in space telescope data. The blue areas indicate pixels that the AI model thinks are invalid. Artifact InSPECtor volunteers will learn how to verify whether the machine got it right.

Credit: Image data from the ESA/Euclid Q1 Data release. Image processing by Aimee Schechter and Bharath C. Nagam.

Learn More and Get Involved

This is the hidden content, please

• Sign In
• or
• Sign Up

Artifact InSPECtor

Train the tools used to remove artifacts from the data collected by space telescopes. For anyone with a smartphone or laptop.

This is the hidden content, please

• Sign In
• or
• Sign Up

logo

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

logo

This is the hidden content, please

• Sign In
• or
• Sign Up

Linkedin logo

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up