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

• Published in: Monthly notices of the Royal Astronomical Society Vol. 505; no. 3; pp. 3982 - 3997
• Main Authors: Bianco, Michele, Giri, Sambit K, Iliev, Ilian T, Mellema, Garrelt
• Format: Journal Article
• Language: English
• Published: Oxford University Press 01.08.2021
• Subjects: dark ages; early Universe; first stars; image processing; interferometric; reionization; image processing; interferometric; early Universe; dark ages, reionization, first stars
• ISSN: 0035-8711; 1365-2966; 1365-2966
• DOI: 10.1093/mnras/stab1518

ABSTRACT The upcoming Square Kilometre Array (SKA-Low) will map the distribution of neutral hydrogen during reionization and produce a tremendous amount of three-dimensional tomographic data. These image cubes will be subject to instrumental limitations, such as noise and limited resolution. Here, we present SegU-Net, a stable and reliable method for identifying neutral and ionized regions in these images. SegU-Net is a U-Net architecture-based convolutional neural network 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 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 the size distributions and Betti numbers, with a relative difference of only a few per cent from the values derived from the original smoothed and then binarized neutral fraction field. These summary statistics characterize the non-Gaussian nature of the reionization process.