The 21-cm bispectrum from neutral hydrogen islands at z < 6

TL;DR

This paper predicts a strong, non-Gaussian 21-cm bispectrum signal at redshifts below 6 due to neutral hydrogen islands, which can be detected by SKA1-LOW, providing insights into late cosmic reionization.

Contribution

It introduces the first detailed prediction of the 21-cm bispectrum from neutral hydrogen islands at z<6, highlighting its detectability and distinctive features.

Findings

The 21-cm bispectrum is significantly larger in models with late reionization.

A characteristic scale of ~1 cMpc$^{-1}$ imprints a feature in the bispectrum.

Detection is feasible with SKA1-LOW after 1080 hours of observation.

Abstract

Spatial variations in the Lyman-$\alpha$ forest opacity at $z<6$ seem to require a late end to cosmic reionization. In this picture, the universe contains neutral hydrogen 'islands' of up to 100 cMpc$/h$ in extent down to redshifts as low as $z\sim 5.3$. This delayed end to reionization also seems to be corroborated by various other observables. An implication of this scenario is that the power spectrum of the cosmological 21-cm signal at $z<6$ is enhanced relative to conventional reionization models by orders of magnitude. However, these neutral hydrogen islands are also predicted to be at the locations of the deepest voids in the cosmological large-scale structure. As a result, the distribution of the 21-cm signal from them is highly non-Gaussian. We derive the 21-cm bispectrum signal from these regions using high-dynamic-range radiative transfer simulations of reionization. We find that relative to conventional models in which reionization is complete at $z>6$, our model has a significantly larger value of the 21-cm bispectrum. The neutral islands also imprint a feature in the isosceles bispectrum at a characteristic scale of $\sim 1$ cMpc$^{-1}$. We also study the 21-cm bispectrum for general triangle configuration by defining a triangle index. It should be possible to detect the 21-cm bispectrum signal at $\nu\gtrsim 200$ MHz using SKA1-LOW for 1080 hours of observation, assuming optimistic foreground removal.