Scientists Used AI to Create a Hyper Detailed 3D Map of Stars, Galaxies, and Quasars:
A team of astronomers from the University of Hawaiʻi at Mānoa's Institute for Astronomy (IfA) has produced the most comprehensive astronomical imaging catalog of stars, galaxies, and quasars ever created with help from an artificially intelligent neural network.
The group of astronomers from the University of Hawaiʻi at Mānoa's Institute for Astronomy (IfA) released a catalog containing 3 billion celestial objects in 2016, including stars, galaxies, and quasars (the active cores of supermassive black holes). Needless to say, the parsing of this extensive database—packed with 2 petabytes of data—was a task unfit for puny humans, and even grad students. A major goal coming out of the 2016 catalog release was to better characterize these distant specks of light, and to also map the arrangement of galaxies in all three dimensions. The Pan-STARRS team can now check these items off their to-do list, owing to the powers of machine learning. The results of their work have been published to the Monthly Notices of the Royal Astronomical Society.
Journal Reference:
Beck, Róbert, Szapudi, István, Flewelling, Heather, et al. PS1-STRM: Neural network source classification and photometric redshift catalogue for PS1 3π DR1, Monthly Notices of the Royal Astronomical Society (DOI: 10.1093/mnras/staa2587)
(Score: 2, Insightful) by Anonymous Coward on Thursday October 15 2020, @02:24PM (3 children)
The scientists were surprised to find, on the whole, the 3D structure of the Universe has the same structure as their training data set!
(Score: 2) by leon_the_cat on Thursday October 15 2020, @03:40PM (1 child)
Which it seems is their own data from PS1 telescope ( dunno why they haven't got a PS4 or PS5 yet?!!). They do compare themselves to Sloan Digital Sky Survey, do they use any data from it? Planck satellite data used?
(Score: 2) by takyon on Thursday October 15 2020, @06:05PM
Gaia [wikipedia.org] looks like a good comparison. They are also using their data to build a 3D map.
[SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]
(Score: 2) by pdfernhout on Friday October 16 2020, @03:24PM
https://joelgrus.com/2016/05/23/fizz-buzz-in-tensorflow/ [joelgrus.com]
Seriously though, there is a star I'd like to get more info on, like if it had planets:
https://nonprofit.adoptastar.org/stars/219100763 [adoptastar.org]
Adopted in memory of someone dear to me and now gone who wanted to be an astronomer/astrophysicist long ago...
The biggest challenge of the 21st century: the irony of technologies of abundance used by scarcity-minded people.