Astronomers train AI to reveal the true shape of galaxies

A new artificial intelligence method removes the effect of gravity on cosmic images, showing the real shapes of distant galaxies.

Astronomers train AI to reveal the true shape of galaxies
  • Japanese astronomers train AI to differentiate between fake and real data from faraway galaxies.
  • The approach helps remove noise from astronomical observations.
  • The new technique will help more accurately reveal the large-scale structure of the universe.

    • A new AI-based tool developed by Japanese astronomers promises to remove unwanted noise in data to generate a cleaner view of the true shape of galaxies. The scientists successfully tried this approach on real data from Japan's Subaru Telescope and discovered that the distribution of mass produced by their technique corresponded to the established models.

      The scientists from the National Astronomical Observatory of Japan (NAOJ) in Tokyo believe their method could be very useful in the analysis of big data from large astronomy surveys. These surveys help us study the structure of the universe by focusing on gravitational lensing patterns.

      The trouble with gravitational lensing

      Gravitational lensing refers to the phenomenon whereby massive space objects like a cluster of galaxies can distort or bend the light that comes from objects in their background. In other words, images of distant space bodies can be made to look strange by the gravitational pull of objects in the foreground.

      One example of this is the "Eye of Horus" galaxy system, discovered by NAOJ astronomers in 2016. The striking images of the system, named in honor of the sacred eye of an ancient Egyptian sky god, are the byproduct of two distant galaxies being lensed by a closer galaxy.

      The issue with gravitational lensing for astronomers is that it can make it hard to differentiate galaxy images that are distorted by gravity from galaxies that are actually distorted. This so-called "shape noise" undermines confidence in research into the universe's large structures.

      Eye of Horus galaxy system. The yellow object at the center represents a galaxy about 7 billion light-years away that bends the light from two galaxies in the background that are even farther away.Credit: NAOJ

      A new approach

      The new study, published in the Monthly Notices of the Royal Astronomical Society, shows how the research team was able to counteract shape noise by utilizing ATERUI II, the most powerful astronomy supercomputer in the world. By feeding it pretend and real data from the Subaru Telescope, the scientists had the computer simulate 25,000 mock galaxy catalogs. They added realistic noise to these data sets while teaching their artificial intelligence network through deep learning to pick out the correct data from the noise.

      "This research shows the benefits of combining different types of research: observations, simulations, and AI data analysis," shared team's leader Masato Shirasaki. He added, "In this era of big data, we need to step across traditional boundaries between specialties and use all available tools to understand the data. If we can do this, it will open new fields in astronomy and other sciences."

      How the AI works

      Employing a generative adversarial network (GAN), the Japanese astronomers' AI learned to find details that previously could not be seen, explained the observatory's press release. The GAN developed by the scientists actually uses two networks — one of them generates an image of a lens map without noise, while the other one compares it to the real noise-free lens map, tagging the created images as a fake. By running this system through a large number of noise and denoised map pairs, both of the networks are trained. The first one makes lens maps that are closer to the real ones, while the other network does a better job of identifying fakes.

      The diagram of the AI (generative adversarial network) utilized in the study. Credit: NAOJ

      To further test their method, the scientists turned their AI's attention to real data from 21 square degrees of the sky, showing that the distribution of foreground mass is in accordance with what is predicted by the standard cosmological model.

          3,000-pound Triceratops skull unearthed in South Dakota

          "You dream about these kinds of moments when you're a kid," said lead paleontologist David Schmidt.

          Excavation of a triceratops skull in South Dakota.

          Credit: David Schmidt / Westminster College
          Surprising Science
          • The triceratops skull was first discovered in 2019, but was excavated over the summer of 2020.
          • It was discovered in the South Dakota Badlands, an area where the Triceratops roamed some 66 million years ago.
          • Studying dinosaurs helps scientists better understand the evolution of all life on Earth.
          Keep reading Show less

          An Olympics without fanfare: What would the ancient Greeks think of the empty stadiums?

          In ancient Greece, the Olympics were never solely about the athletes themselves.

          Photo by Despina Galani on Unsplash

          Because of a dramatic rise in COVID-19 cases, the opening and closing ceremonies of the 2021 Olympics will unfold in a stadium absent the eyes, ears and voices of a once-anticipated 68,000 ticket holders from around the world.

          Keep reading Show less

          Bad at math? Blame your neurotransmitters

          A new brain imaging study explored how different levels of the brain's excitatory and inhibitory neurotransmitters are linked to math abilities.

          Signal burst illustration

          Mind & Brain
          • Glutamate and GABA are neurotransmitters that help regulate brain activity.
          • Scientists have long known that both are important to learning and neuroplasticity, but their relationship to acquiring complex cognitive skills like math has remained unclear.
          • The new study shows that having certain levels of these neurotransmitters predict math performance, but that these levels switch with age.
          Keep reading Show less