Abstract

Contributed Talk - Splinter EScience

Friday, 17 September 2021, 09:40   (virtual ESc)

Learning from 3D tomographic 21cm intensity data

Caroline Heneka (1), Steffen Neutsch (1), Michele delli Veneri (2), Bernardo Fraga (3), Andrew Soroka (4)
(1) Universität Hamburg, (2) University of Naples, (3) CBPF Brazilian Center for Research in Physics, (4) Moskow State University

Intensity Mapping (IM) of line emission targets the Universe from present time up to redshifts beyond ten when the Universe reionized and the first galaxies formed, from small to largest scales. Imaging the 21cm signal, with redshift dependency added through frequency, will result in 3D lightcone data that gives valuable insight into the growth of structure, the inter-galactic medium as well as properties and environment of ionising sources. Due to the huge amount of data that radio interferometers, and especially the Square Kilometre Array (SKA) will produce, as well as the highly non-Gaussian nature of the fluctuation signal measured, these data necessitate the development of new methods beyond e.g. power spectrum measurements of fluctuations. In this talk I showcase the use of deep networks that are tailored for the 3D structure of tomographic 21cm lightcones of reionisation and cosmic dawn to to directly infer e.g. dark matter and astrophysical properties without an underlying Gaussian assumption. I compare different architectures and highlight how a relatively simple 3D convolutional network architecture can be constructed to become the best-performing one. I finish by a glimpse at lower redshift results for the recent SKA Science Data Challenge 2, where hydrogen sources where to be detected and characterised in a large (TB) low signal-to-noise datacube of the hydrogen 21cm line. I will highlight lessons learned on the application of a range of machine learning methods and architectures on such types of datacubes.