Nonlinear reconstruction of 21cm global signal from 21cm power spectrum with artificial neural networks

TL;DR

This paper introduces a neural network-based method to reconstruct the 21cm global signal from the power spectrum, enabling cross-validation of different observational techniques in 21cm cosmology.

Contribution

It presents a novel ANN approach that accurately recovers the 21cm global signal from the power spectrum across a wide redshift range, even with realistic noise.

Findings

Accurately reconstructs the 21cm global signal from simulated data.

Effective even with realistic thermal noise levels.

Facilitates cross-validation between different 21cm observational methods.

Abstract

In this paper, we propose a novel method to recover the 21cm global signal from the 21cm power spectrum using artificial neural networks (ANNs). The 21cm global signal is crucial for understanding cosmic evolution from the Dark Ages through the Epoch of Reionization (EoR). While interferometers like LOFAR, MWA, HERA, and SKA focus on detecting the 21cm power spectrum, single-dish experiments such as EDGES target the global signal. Our method utilizes ANNs to establish a connection between these two observables, providing a means to cross-validate independent 21cm line observations. This capability is significant as it allows different observational approaches to verify each other's results, ensuring greater reliability in 21cm cosmology. We demonstrate that our ANN-based approach can accurately recover the 21cm global signal across a wide redshift range (z=7.5-35) from simulated data, even when realistic thermal noise levels, such as those expected from SKA-1, are considered. This cross-validation process strengthens the robustness of 21cm signal analysis, offering a more comprehensive understanding of the early universe.