A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs

Abstract

Creating a database of 21cm brightness temperature signals from the Epoch of Reionisation (EoR) for an array of reionisation histories is a complex and computationally expensive task, given the range of astrophysical processes involved and the possibly high-dimensional parameter space that is to be probed. We utilise a specific type of neural network, a Progressively Growing Generative Adversarial Network (PGGAN), to produce realistic tomography images of the 21cm brightness temperature during the EoR, covering a continuous three-dimensional parameter space that models varying X-ray emissivity, Lyman band emissivity, and ratio between hard and soft X-rays. The GPU-trained network generates new samples at a resolution of $\sim 3^{\prime }$ in a second (on a laptop CPU), and the resulting global 21cm signal, power spectrum, and pixel distribution function agree well with those of the training data, taken from the 21SSD catalogue \citep{Semelin2017}. Finally, we showcase how a trained PGGAN can be leveraged for the converse task of inferring parameters from 21cm tomography samples via Approximate Bayesian Computation.

15 pages, 8+1 figures, accepted by MNRAS

References in corpus (21)

• Conditional Generative Adversarial Nets
• Cosmology at Low Frequencies: The 21 cm Transition and the High-Redshift Universe
• UV Luminosity Functions at redshifts z~4 to z~10: 10000 Galaxies from HST Legacy Fields
• Towards Principled Methods for Training Generative Adversarial Networks
• 21 cm fluctuations from inhomogeneous X-ray heating before reionization
• 21CMMC: an MCMC analysis tool enabling astrophysical parameter studies of the cosmic 21 cm signal
• Signature of Excess Radio Background in the 21-cm Global Signal and Power Spectrum
• First Season MWA EoR Power Spectrum Results at Redshift 7
• Improving the Epoch of Reionization Power Spectrum Results from Murchison Widefield Array Season 1 Observations
• Do GANs actually learn the distribution? An empirical study
• Fast Large-Scale Reionization Simulations
• Generating Diverse High-Fidelity Images with VQ-VAE-2
• The simulated 21 cm signal during the epoch of reionization : full modeling of the Ly-alpha pumping
• First Season MWA Phase II EoR Power Spectrum Results at Redshift 7
• Emulation of reionization simulations for Bayesian inference of astrophysics parameters using neural networks
• Lyman-alpha radiative transfer during the Epoch of Reionization: contribution to 21-cm signal fluctuations
• Radio background and IGM heating due to Pop III supernovae explosions
• 21SSD: a public database of simulated 21-cm signals from the epoch of reionization
• HIGAN: Cosmic Neutral Hydrogen with Generative Adversarial Networks
• Astro 2020 Science White Paper: Fundamental Cosmology in the Dark Ages with 21-cm Line Fluctuations
• Astro2020 Science White Paper: Insights Into the Epoch of Reionization with the Highly-Redshifted 21-cm Line