Estimation of HII Bubble Size Distribution from 21cm Power Spectrum with Artificial Neural Networks

Abstract

The bubble size distribution of ionized hydrogen regions probes the information about the morphology of \HII\ bubbles during the reionization. Conventionally, the \HII\ bubble size distribution can be derived from the tomographic imaging data of the redshifted 21~cm signal from the epoch of reionization, which, however, is observationally challenging even for the upcoming large radio interferometer arrays. Given that these interferometers promise to measure the 21~cm power spectrum accurately, we propose a new method, which is based on the artificial neural networks (ANN), to reconstruct the \HII\ bubble size distribution from the 21~cm power spectrum. We demonstrate that the reconstruction from the 21~cm power spectrum can be almost as accurate as directly measured from the imaging data with the fractional error $\lesssim 10\%$, even with thermal noise at the sensitivity level of the Square Kilometre Array. Nevertheless, the reconstruction implicitly exploits the modelling in reionization simulations, and hence the recovered \HII\ bubble size distribution is not an independent summary statistic from the power spectrum, and should be used only as the indicator for understanding \HII\ bubble morphology and its evolution.