Restoring Missing Modes of 21cm Intensity Mapping with Deep Learning: Impact on BAO Reconstruction

TL;DR

This paper uses deep learning to recover missing Fourier modes in 21cm intensity mapping caused by foreground contamination, improving BAO reconstruction accuracy without significant bias.

Contribution

It introduces a U-Net based deep learning method to restore lost modes in contaminated 21cm maps, enhancing BAO analysis in large-scale structure studies.

Findings

High correlation (~0.9) between restored and original maps at k~1 h/Mpc.

AI restoration minimally impacts BAO reconstruction performance.

Models trained on coarser data generalize well to finer data, leveraging scale-invariance.

Abstract

In 21cm intensity mapping of the large-scale structure (LSS), regions in Fourier space could be compromised by foreground contamination. In interferometric observations, this contamination, known as the foreground wedge, is exacerbated by the chromatic response of antennas, leading to substantial data loss. Meanwhile, the baryonic acoustic oscillation (BAO) reconstruction, which operates in configuration space to "linearize" the BAO signature, offers improved constraints on the sound horizon scale. However, missing modes within these contaminated regions can negatively impact the BAO reconstruction algorithm. To address this challenge, we employ the deep learning model U-Net to recover the lost modes before applying the BAO reconstruction algorithm. Despite hardware limitations, such as GPU memory, our results demonstrate that the AI-restored 21cm temperature map achieves a high correlation with the original signal, with a correlation ratio of approximately $0.9$ at $k \sim 1 h/Mpc$. Furthermore, subsequent BAO reconstruction indicates that the AI restoration has minimal impact on the performance of the `linearized' BAO signal, proving the effectiveness of the machine learning approach to mitigate the impact of foreground contamination. Interestingly, we demonstrate that the AI model trained on coarser fields can be effectively applied to finer fields, achieving even higher correlation. This success is likely attributable to the scale-invariance properties of non-linear mode coupling in large-scale structure and the hierarchical structure of the U-Net architecture.