Emulation of the cosmic dawn 21-cm power spectrum and classification of excess radio models using an artificial neural network

Sudipta Sikder*, Rennan Barkana*, Itamar Reis, Anastasia Fialkov

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

The cosmic 21-cm line of hydrogen is expected to be measured in detail by the next generation of radio telescopes. The enormous data set from future 21-cm surveys will revolutionize our understanding of early cosmic times. We present a machine learning approach based on an artificial neural network that uses emulation in order to uncover the astrophysics in the epoch of reionization and cosmic dawn. Using a seven-parameter astrophysical model that covers a very wide range of possible 21-cm signals, over the redshift range 6 to 30 and wavenumber range 0.05 to 1 Mpc−1 we emulate the 21-cm power spectrum with a typical accuracy of 10 − 20 per cent. As a realistic example, we train an emulator using the power spectrum with an optimistic noise model of the square kilometre array (SKA). Fitting to mock SKA data results in a typical measurement accuracy of 2.8 per cent in the optical depth to the cosmic microwave background, 34 per cent in the star-formation efficiency of galactic haloes, and a factor of 9.6 in the X-ray efficiency of galactic haloes. Also, with our modelling we reconstruct the true 21-cm power spectrum from the mock SKA data with a typical accuracy of 15 − 30 per cent. In addition to standard astrophysical models, we consider two exotic possibilities of strong excess radio backgrounds at high redshifts. We use a neural network to identify the type of radio background present in the 21-cm power spectrum, with an accuracy of 87 per cent for mock SKA data.

Original languageEnglish
Pages (from-to)9977-9998
Number of pages22
JournalMonthly Notices of the Royal Astronomical Society
Volume527
Issue number4
DOIs
StatePublished - 1 Feb 2024

Funding

FundersFunder number
National Aeronautics and Space Administration
Ambrose Monell Foundation
Institute for Advanced Study
Royal Society2020
Israel Science Foundation2359/20

    Keywords

    • cosmology: theory
    • dark ages, reionization, first stars
    • methods: numerical
    • methods: statistical

    Fingerprint

    Dive into the research topics of 'Emulation of the cosmic dawn 21-cm power spectrum and classification of excess radio models using an artificial neural network'. Together they form a unique fingerprint.

    Cite this