A Generative Modeling Approach to Reconstructing 21-cm Tomographic Data

TL;DR

This paper presents a deep generative model that reconstructs lost 21-cm cosmological data from foreground contamination, enabling better analysis of the early universe during cosmic dawn and reionization.

Contribution

It introduces a novel stochastic interpolant-based generative model that effectively restores wedge-filtered 21-cm data by leveraging the non-Gaussian features of the signal.

Findings

Successfully reconstructs 21-cm data from wedge filtering.

Restores spatial information across different cosmological scenarios.

Offers a new tool for analyzing cosmic dawn and reionization epochs.

Abstract

Analyses of the cosmic 21-cm signal are hampered by astrophysical foregrounds that are far stronger than the signal itself. These foregrounds, typically confined to a wedge-shaped region in Fourier space, often necessitate the removal of a vast majority of modes, thereby degrading the quality of the data anisotropically. To address this challenge, we introduce a novel deep generative model based on stochastic interpolants to reconstruct the 21-cm data lost to wedge filtering. Our method leverages the non-Gaussian nature of the 21-cm signal to effectively map wedge-filtered 3D lightcones to samples from the conditional distribution of wedge-recovered lightcones. We demonstrate how our method is able to restore spatial information effectively, considering both varying cosmological initial conditions and astrophysics. Furthermore, we discuss a number of future avenues where this approach could be applied in analyses of the 21-cm signal, potentially offering new opportunities to improve our understanding of the Universe during the epochs of cosmic dawn and reionization.