Using Machine Learning to super-resolve ESA's XMM-Newton X-ray telescope – YouTube

Using Machine Learning to super-resolve ESA's XMM-Newton X-ray telescope



[ad_1]

  • Video Views: 1152
  • Published On: 2022-05-08 22:00:23
  • Video Published/Author: Space Mog
  • Video Duration: 00:07:35
  • Source: Watch on YouTube


Hi Spacecats, I’m Dr Maggie Lieu and welcome to my channel, where you can find all things space, astronomy and physics! My student published his first paper this week on using artificial intelligence to enhance the astronomical images from ESA’s XMM-Newton telescope. So le’ts talk about that.

Links:
Sweere+2022: https://arxiv.org/abs/2205.01152
Jenkins+2008: https://arxiv.org/abs/0801.2356

Media credits:
hubble galaxies: ESA/Hubble/Digitized Sky Survey/Risinger
filament: ESO/Calçada/Subaru/National Astronomical Observatory of Japan/Tanaka
Perseus: ZuHone/Harvard
eROSITA: DLR
Xray photon detection: CXC/D. Berry
NGC 1672 CHANDRA/XMM: Jenkins 2008

Support me through my shop:
www.maggielieu.com/shop

If you enjoyed the video, please consider by liking, sharing and subscribing! I’m also on:
twitter: https://twitter.com/space_mog
instagram: https://instagram.com/space_mog/
facebook: https://facebook.com/spacemog/

[ad_2]

12 comments
  1. Fascinating. This kind of AI image processing really seems to be taking off. Strangely enough I've been looking into some of the amazing work that's coming out of AI generated art at the moment and it seems to be using a kind of inverted version of the algorithms discussed in this video, except that instead of working back to a genuine underlying reality from a noisy signal, it's being guided by something called CLIP to pull artwork out of pure noise (Disco Diffusion & Night Cafe are two existing examples of software you can play with now and better things are coming). Loved hearing about this piece of research.

Leave a Reply

Your email address will not be published.

Related Posts
Total
0
Share