Separating the EoR signal with a convolutional denoising autoencoder: a deep-learning-based method

Abstract When applying the foreground removal methods to uncover the faint cosmological signal from the epoch of reionization (EoR), the foreground spectra are assumed to be smooth. However, this assumption can be seriously violated in practice since the unresolved or mis-subtracted foreground sourc...

Full description

Saved in:
Bibliographic Details
Published in:Monthly notices of the Royal Astronomical Society Vol. 485; no. 2; pp. 2628 - 2637
Main Authors: Li, Weitian, Xu, Haiguang, Ma, Zhixian, Zhu, Ruimin, Hu, Dan, Zhu, Zhenghao, Gu, Junhua, Shan, Chenxi, Zhu, Jie, Wu, Xiang-Ping
Format: Journal Article
Language:English
Published: Oxford University Press 11.05.2019
Subjects:
radio continuum: general
methods: data analysis
techniques: interferometric
dark ages, reionization, first stars
ISSN:0035-8711, 1365-2966
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract When applying the foreground removal methods to uncover the faint cosmological signal from the epoch of reionization (EoR), the foreground spectra are assumed to be smooth. However, this assumption can be seriously violated in practice since the unresolved or mis-subtracted foreground sources, which are further complicated by the frequency-dependent beam effects of interferometers, will generate significant fluctuations along the frequency dimension. To address this issue, we propose a novel deep-learning-based method that uses a nine-layer convolutional denoising autoencoder (CDAE) to separate the EoR signal. After being trained on the SKA images simulated with realistic beam effects, the CDAE achieves excellent performance as the mean correlation coefficient ($\bar{\rho }$) between the reconstructed and input EoR signals reaches 0.929 ± 0.045. In comparison, the two representative traditional methods, namely the polynomial fitting method and the continuous wavelet transform method, both have difficulties in modelling and removing the foreground emission complicated with the beam effects, yielding only $\bar{\rho }_{\mathrm{poly}} = {0.296 \pm 0.121}$ and $\bar{\rho }_{\mathrm{cwt}} = {0.198 \pm 0.160}$, respectively. We conclude that, by hierarchically learning sophisticated features through multiple convolutional layers, the CDAE is a powerful tool that can be used to overcome the complicated beam effects and accurately separate the EoR signal. Our results also exhibit the great potential of deep-learning-based methods in future EoR experiments.
ISSN:0035-8711
1365-2966
DOI:10.1093/mnras/stz582