Predicting 21cm-line map from Lyman $\alpha$ emitter distribution with Generative Adversarial Networks

Abstract

The radio observation of 21\,cm-line signal from the Epoch of Reionization (EoR) enables us to explore the evolution of galaxies and intergalactic medium in the early universe. However, the detection and imaging of the 21\,cm-line signal are tough due to the foreground and instrumental systematics. In order to overcome these obstacles, as a new approach, we propose to take a cross correlation between observed 21\,cm-line data and 21\,cm-line images generated from the distribution of the Lyman-$\alpha$ emitters (LAEs) through machine learning. In order to create 21\,cm-line maps from LAE distribution, we apply conditional Generative Adversarial Network (cGAN) trained with the results of our numerical simulations. We find that the 21\,cm-line brightness temperature maps and the neutral fraction maps can be reproduced with correlation function of 0.5 at large scales $k<0.1{\mathrm{Mpc}}^{-1}$. Furthermore, we study the detectability of the the cross correlation assuming the the LAE deep survey of the Subaru Hyper Suprime Cam, the 21\,cm observation of the MWA Phase II and the presence of the foreground residuals. We show that the signal is detectable at $k<0.1{\mathrm{Mpc}}^{-1}$ with 1000 hours of MWA observation even if the foreground residuals are 5 times larger than the 21\,cm-line power spectrum. Our new approach of cross correlation with image construction using the cGAN can not only boost the detectability of EoR 21\,cm-line signal but also allow us to estimate the 21\,cm-line auto-power spectrum.

16 pages, 12 figures, 4 tables, revised version

References in corpus (19)

• Cosmology at Low Frequencies: The 21 cm Transition and the High-Redshift Universe
• Improved upper limits on the 21-cm signal power spectrum of neutral hydrogen at $\mathbf{z}\approx 9.1$ from LOFAR
• Foreground simulations for the LOFAR - Epoch of Reionization Experiment
• Deep multi-redshift limits on Epoch of Reionisation 21cm Power Spectra from Four Seasons of Murchison Widefield Array Observations
• Prime Focus Spectrograph (PFS) for the Subaru Telescope: Overview, recent progress, and future perspectives
• Improving the Epoch of Reionization Power Spectrum Results from Murchison Widefield Array Season 1 Observations
• The Scale of the Problem : Recovering Images of Reionization with GMCA
• Probing Reionization with the 21 cm-Galaxy Cross Power Spectrum
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Emulation of reionization simulations for Bayesian inference of astrophysics parameters using neural networks
• deep21: a Deep Learning Method for 21cm Foreground Removal
• Separating the EoR Signal with a Convolutional Denoising Autoencoder: A Deep-learning-based Method
• HIGAN: Cosmic Neutral Hydrogen with Generative Adversarial Networks
• SILVERRUSH X: Machine Learning-Aided Selection of $9318$ LAEs at $z=2.2$, $3.3$, $4.9$, $5.7$, $6.6$, and $7.0$ from the HSC SSP and CHORUS Survey Data
• Deep learning for intensity mapping observations: Component extraction
• A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs
• A black box for dark sector physics: Predicting dark matter annihilation feedback with conditional GANs
• The spin-temperature dependence of the 21cm -- LAE cross-correlation
• Predictions for the 21cm-galaxy cross-power spectrum observable with SKA and future galaxy surveys

Cited by in corpus (7)

• Deep learning approach for identification of HII regions during reionization in 21-cm observations
• Machine Learning for Observational Cosmology
• Exploring the cosmic dawn and epoch of reionization with 21cm line
• Decoding Dark Matter Substructure without Supervision
• Constraining the 21cm brightness temperature of the IGM at $z$=6.6 around LAEs with the Murchison Widefield Array
• Stochastic Super-resolution of Cosmological Simulations with Denoising Diffusion Models
• Nonlinear reconstruction of 21cm global signal from 21cm power spectrum with artificial neural networks