Deep learning approach for identification of HII regions during reionization in 21-cm observations -- III. image recovery

Abstract

The low-frequency component of the upcoming Square Kilometre Array Observatory (SKA-Low) will be sensitive enough to construct 3D tomographic images of the 21-cm signal distribution during reionisation. However, foreground contamination poses challenges for detecting this signal, and image recovery will heavily rely on effective mitigation methods. We introduce \texttt{SERENEt}, a deep-learning framework designed to recover the 21-cm signal from SKA-Low's foreground-contaminated observations, enabling the detection of ionised (HII) and neutral (HI) regions during reionisation. \texttt{SERENEt} can recover the signal distribution with an average accuracy of 75 per cent at the early stages (${\overline{x}}_{\mathrm{HI}}\simeq 0.9$) and up to 90 per cent at the late stages of reionisation (${\overline{x}}_{\mathrm{HI}}\simeq 0.1$). Conversely, HI region detection starts at 92 per cent accuracy, decreasing to 73 per cent as reionisation progresses. Beyond improving image recovery, \texttt{SERENEt} provides cylindrical power spectra with an average accuracy exceeding 93 per cent throughout the reionisation period. We tested \texttt{SERENEt} on a 10-degree field-of-view simulation, consistently achieving better and more stable results when prior maps were provided. Notably, including prior information about HII region locations improved 21-cm signal recovery by approximately 10 per cent. This capability was demonstrated by supplying \texttt{SERENEt} with ionising source distribution measurements, showing that high-redshift galaxy surveys of similar observation fields can optimise foreground mitigation and enhance 21-cm image construction.

17 pages, 15 figures, 1 table

References in corpus (81)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Array Programming with NumPy
• Seven-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Cosmological Interpretation
• scikit-image: Image processing in Python
• Cosmology at Low Frequencies: The 21 cm Transition and the High-Redshift Universe
• The Murchison Widefield Array: the Square Kilometre Array Precursor at low radio frequencies
• 21-cm cosmology
• An excursion set model of hierarchical clustering: Ellipsoidal collapse and the moving barrier
• 21cmFAST: A Fast, Semi-Numerical Simulation of the High-Redshift 21-cm Signal
• The Growth of HII Regions During Reionization
• Efficient Simulations of Early Structure Formation and Reionization
• 21 Centimeter Fluctuations from Cosmic Gas at High Redshifts
• Improved upper limits on the 21-cm signal power spectrum of neutral hydrogen at $\mathbf{z}\approx 9.1$ from LOFAR
• Non-Linear Evolution of the Bispectrum of Cosmological Perturbations
• The Epoch of Reionization Window: I. Mathematical Formalism
• Foreground simulations for the LOFAR - Epoch of Reionization Experiment
• Deep multi-redshift limits on Epoch of Reionisation 21cm Power Spectra from Four Seasons of Murchison Widefield Array Observations
• The Epoch of Reionization Window: II. Statistical Methods for Foreground Wedge Reduction
• Improved Constraints on the 21 cm EoR Power Spectrum and the X-Ray Heating of the IGM with HERA Phase I Observations
• A Method for 21cm Power Spectrum Estimation in the Presence of Foregrounds
• Foreground Removal using FastICA: A Showcase of LOFAR-EoR
• DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
• HERA Phase I Limits on the Cosmic 21-cm Signal: Constraints on Astrophysics and Cosmology During the Epoch of Reionization
• The Cosmic Dawn and Epoch of Reionization with the Square Kilometre Array
• 21cmFAST v3: A Python-integrated C code forgenerating 3D realizations of the cosmic 21cm signal
• Improving the Epoch of Reionization Power Spectrum Results from Murchison Widefield Array Season 1 Observations
• CRASH: a Radiative Transfer Scheme
• Realistic Simulations of the Galactic Polarized Foreground: Consequences for 21-cm Reionization Detection Experiments
• Statistical 21-cm Signal Separation via Gaussian Process Regression Analysis
• Foregrounds for redshifted 21 cm studies of reionization: GMRT 153 MHz observations
• Quantifying the non-Gaussianity in the EoR 21-cm signal through bispectrum
• Characterizing Foreground for redshifted 21-cm radiation: 150 MHz GMRT observations
• The Evolution of 21-cm Structure (EOS): public, large-scale simulations of Cosmic Dawn and Reionization
• Light cone effect on the reionization 21-cm power spectrum
• Power spectrum extraction for redshifted 21-cm epoch of reionization experiments: the LOFAR case
• Constraining the intergalactic medium at $z\approx$ 9.1 using LOFAR Epoch of Reionization observations
• Non-parametric foreground subtraction for 21cm epoch of reionization experiments
• The Importance of Wide-field Foreground Removal for 21 cm Cosmology: A Demonstration With Early MWA Epoch of Reionization Observations
• Bubble size statistics during reionization from 21-cm tomography
• Higher Order Contributions to the 21 cm Power Spectrum
• Optimal identification of HII regions during reionization in 21-cm observations
• Deep learning dark matter map reconstructions from DES SV weak lensing data
• The 21cm bispectrum as a probe of non-Gaussianities due to X-ray heating
• Imaging the redshifted 21-cm pattern around the first sources during the cosmic dawn using the SKA
• The 21cm bispectrum during reionization: a tracer of the ionization topology
• deep21: a Deep Learning Method for 21cm Foreground Removal
• Comparing Foreground Removal Techniques for Recovery of the LOFAR-EoR 21cm Power Spectrum
• Visibility based angular power spectrum estimation in low frequency radio interferometric observations
• Gaussian Process Foreground Subtraction and Power Spectrum Estimation for 21 cm Cosmology
• Position-dependent power spectra of the 21-cm signal from the epoch of reionization
• Recovering the Wedge Modes Lost to 21-cm Foregrounds
• Simulating the Impact of X-ray Heating during the Cosmic Dawn
• Separating the EoR Signal with a Convolutional Denoising Autoencoder: A Deep-learning-based Method
• Neutral island statistics during reionization from 21-cm tomography
• Removing Astrophysics in 21 cm maps with Neural Networks
• Deep learning approach for identification of HII regions during reionization in 21-cm observations
• Redshift-space distortions in simulations of the 21-cm signal from the cosmic dawn
• Observing AGN feedback with CO intensity mapping
• Extracting the Subhalo Mass Function from Strong Lens Images with Image Segmentation
• Image segmentation for analyzing galaxy-galaxy strong lensing systems
• MillimeterDL: Deep Learning Simulations of the Microwave Sky
• BEoRN: A fast and flexible framework to simulate the epoch of reionisation and cosmic dawn
• Deep learning approach for identification of HII regions during reionization in 21-cm observations -- II. foreground contamination
• Single frequency CMB B-mode inference with realistic foregrounds from a single training image
• Mass Estimation of Galaxy Clusters with Deep Learning II: CMB Cluster Lensing
• Reconstructing Patchy Reionization with Deep Learning
• Fast and realistic large-scale structure from machine-learning-augmented random field simulations
• CENN: A fully convolutional neural network for CMB recovery in realistic microwave sky simulations
• Machine-learning recovery of foreground wedge-removed 21-cm light cones for high-$z$ galaxy mapping
• Improving constraints on primordial non-Gaussianity using neural network based reconstruction
• Bubble mapping with the Square Kilometer Array -- I. Detecting galaxies with Euclid, JWST, WFIRST and ELT within ionized bubbles in the intergalactic medium at z>6
• Machine Learning and Cosmology
• Exploring the consequences of chromatic data excision in 21-cm Epoch of Reionization power spectrum observations
• Observational challenges in Ly-alpha intensity mapping
• Inpainting CMB maps using Partial Convolutional Neural Networks
• pyC${}^2$Ray: A flexible and GPU-accelerated Radiative Transfer Framework for Simulating the Cosmic Epoch of Reionization
• PINION: Physics-informed neural network for accelerating radiative transfer simulations for cosmic reionization
• 21-cm foreground removal using AI and frequency-difference technique
• Analysing the Epoch of Reionization with three-point correlation functions and machine learning techniques
• Reionisation time fields reconstruction from 21 cm signal maps
• Deep Machine Learning in Cosmology: Evolution or Revolution?

Cited by in corpus (4)

• The 21cm-galaxy cross-correlation: Realistic forecast for 21cm signal detection and reionisation constraints
• Impact of 21-cm foreground mitigation strategies on reionization power spectrum constraints
• Deep learning with hybrid frequency differencing and principal component analysis for 21-cm foreground and beam mitigation
• Beyond the Power Spectrum: A New Framework for Non-Stationary Fields with Applications to Light-Cone Effects in Line Intensity Mapping