Deep learning approach for identification of HII regions during reionization in 21-cm observations

TL;DR

This paper introduces SegU-Net, a CNN-based image segmentation method that accurately identifies ionized and neutral regions in 3D 21-cm observations, aiding the study of reionization with SKA data.

Contribution

The paper presents SegU-Net, a novel U-Net based CNN architecture that improves the accuracy of identifying ionized regions in reionization data and recovers topological statistics effectively.

Findings

SegU-Net achieves over 87% accuracy in estimating ionization history.

The method accurately recovers size distributions and Betti numbers with minimal error.

It outperforms previous segmentation approaches in 21-cm data analysis.

Abstract

The upcoming Square Kilometre Array (SKA-Low) will map the distribution of neutral hydrogen during reionization, and produce a tremendous amount of 3D tomographic data. These images cubes will be subject to instrumental limitations, such as noise and limited resolution. Here we present SegU-Net, a stable and reliable method for identification of neutral and ionized regions in these images. SegU-Net is a U-Net architecture based convolutional neural network (CNN) for image segmentation. It is capable of segmenting our image data into meaningful features (ionized and neutral regions) with greater accuracy compared to previous methods. We can estimate the true ionization history from our mock observation of SKA with an observation time of 1000 h with more than 87 per cent accuracy. We also show that SegU-Net can be used to recover various topological summary statistics, such as size distributions and Betti numbers, with a relative difference of only a few per cent. These summary statistics characterise the non-Gaussian nature of the reionization process.