Extracting the Epoch of Reionization Signal with 3D U-Net Neural Networks Using Data-driven Systematic Effect Model

TL;DR

This paper presents a deep learning approach using 3D U-Net neural networks to extract the Epoch of Reionization signal from simulated SKA-Low images, effectively handling systematic effects, noise, and foreground residuals.

Contribution

The study introduces a novel application of 3D U-Net neural networks for EoR signal extraction, incorporating data-driven models of systematic effects and noise in simulated SKA-Low observations.

Findings

Reliable 2D power spectrum predictions with thermal noise at 1752 hours.

Robust EoR signal detection within the EoR window at extended observation times.

Foreground residuals cause inconsistencies below the horizon delay-line.

Abstract

Neutral hydrogen (HI) serves as a crucial probe for the Cosmic Dawn and the Epoch of Reionization (EoR). Actual observations of the 21-cm signal often encounter challenges such as thermal noise and various systematic effects. To overcome these challenges, we simulate SKA-Low-depth images in South Celestial Pole (SCP) field and process them with a deep learning method. We utilized foreground residuals acquired by LOFAR during actual North Celestial Pole (NCP) field observations, thermal and excess variances calculated via Gaussian process regression (GPR), and 21-cm signals generated with 21cmFAST for signal extraction tests. Our approach to overcome these foreground, thermal noise, and excess variance components employs a 3D U-Net neural network architecture for image analysis. When considering thermal noise corresponding to 1752 hours of integration time, U-Net provides reliable 2D power spectrum predictions, and robustness tests ensure that we get realistic EoR signals. Adding foreground residuals, however, causes inconsistencies below the horizon delay-line. Lastly, evaluating both thermal noise and excess variances with observations up to 4380 hours and 13140 hours ensures reliable power spectrum estimations within the EoR window and across nearly all scales, respectively. The incoherence of excess variances in the frequency direction can greatly affect deep learning to extract 21-cm signals.