From ANN to BNN: Inferring Reionization Parameters using Uncertainty-aware Emulators of 21-cm Summaries
arXiv:2508.13261 · doi:10.1088/1475-7516/2025/12/055
Abstract
Inferring astrophysical parameters from radio interferometric observations of the redshifted 21-cm signal from the Epoch of Reionization (EoR) is a challenging yet crucial task. The 21-cm signal from EoR is expected to be highly non-Gaussian; therefore, we need to use higher-order statistics, e.g., bispectrum. Moreover, the forward modeling of the signal and its statistics for a varying set of model parameters requires rerunning the simulations many times, which is computationally very expensive. To overcome this challenge, many artificial neural network (ANN) based emulators have been introduced, which produce the 21-cm summaries in a fraction of the time. However, ANN emulators have a drawback: they can only produce point-value predictions; thus, they fail to capture the uncertainty associated with their predictions. Therefore, when such emulators are used in the Bayesian inference pipeline, they cannot naturally propagate their prediction uncertainties to the estimated model parameters. To address this problem, we have developed Bayesian neural network (BNN) emulators for the 21-cm signal statistics, which provide the posterior distribution of the predicted signal statistics, including their prediction uncertainty. We use these BNN emulators in our Bayesian inference pipeline to infer the EoR parameters through 21-cm summaries of the mock observation of 21-cm signal with telescopic noise for hr of SKA-LOW observation. We show that BNN emulators can capture the prediction uncertainty for the 21-cm power spectrum and bispectrum, and using these emulators in the inference pipeline provides better and tighter constraints on them. We reduced the training dataset and showed that, for smaller training datasets, BNN outperforms the ANN emulators. We also show that using the bispectrum as a summary statistic gives better constraints on EoR parameters than the power spectrum.
Published version; 31 pages, 7 figures, 3 tables
References in corpus (81)
- Seven-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Cosmological Interpretation
- A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
- Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods
- Cosmology at Low Frequencies: The 21 cm Transition and the High-Redshift Universe
- 21-cm cosmology
- Evidence for Reionization at z ~ 6: Detection of a Gunn-Peterson Trough in a z=6.28 Quasar
- Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
- A Survey of z>5.7 Quasars in the Sloan Digital Sky Survey II: Discovery of Three Additional Quasars at z>6
- Statistics of 207 Lya Emitters at a Redshift Near 7: Constraints on Reionization and Galaxy Formation Models
- The Growth of HII Regions During Reionization
- Simulating Cosmic Reionization at Large Scales I: the Geometry of Reionization
- Reionization and the Cosmic Dawn with the Square Kilometre Array
- Late-time cosmology with 21cm intensity mapping experiments
- A simulation calibrated limit on the HI power spectrum from the GMRT Epoch of Reionization experiment
- Improved upper limits on the 21-cm signal power spectrum of neutral hydrogen at from LOFAR
- Simulating Cosmic Reionization at Large Scales II: the 21-cm Emission Features and Statistical Signals
- Probing Primordial Non-Gaussianity with Large-Scale Structure
- First Results from HERA Phase I: Upper Limits on the Epoch of Reionization 21 cm Power Spectrum
- Primordial non-Gaussianity and Bispectrum Measurements in the Cosmic Microwave Background and Large-Scale Structure
- Inside-out or Outside-in: The topology of reionization in the photon-starved regime suggested by Lyman-alpha forest data
- 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
- First Results from the Lyman Alpha Galaxies in the Epoch of Reionization (LAGER) Survey: Cosmological Reionization at z ~ 7
- Improving the Epoch of Reionization Power Spectrum Results from Murchison Widefield Array Season 1 Observations
- Quantifying the non-Gaussianity in the EoR 21-cm signal through bispectrum
- Light cone effect on the reionization 21-cm power spectrum
- Emulating Simulations of Cosmic Dawn for 21cm Power Spectrum Constraints on Cosmology, Reionization, and X-ray Heating
- The first power spectrum limit on the 21-cm signal of neutral hydrogen during the Cosmic Dawn at z=20-25 from LOFAR
- Constraining the intergalactic medium at 9.1 using LOFAR Epoch of Reionization observations
- Deep learning from 21-cm tomography of the Cosmic Dawn and Reionization
- Analysing the 21cm signal from the Epoch of Reionization with artificial neural networks
- On the use of semi-numerical simulations in predicting the 21-cm signal from the epoch of reionization
- Emulation of reionization simulations for Bayesian inference of astrophysics parameters using neural networks
- Tight Constraints on the Excess Radio Background at from LOFAR
- Interpreting LOFAR 21-cm signal upper limits at z~9.1 in the context of high-z galaxy and reionisation observations
- Probing non-Gaussian features in the HI distribution at the epoch of reionization
- High-redshift post-reionization cosmology with 21cm intensity mapping
- Constraining the astrophysics and cosmology from 21cm tomography using deep learning with the SKA
- Simulation-Based Inference of Reionization Parameters From 3D Tomographic 21 cm Lightcone Images
- Light cone effect on the reionization 21-cm signal II: Evolution, anisotropies and observational implications
- Optimal identification of HII regions during reionization in 21-cm observations
- 21cm-line bispectrum as method to probe Cosmic Dawn and Epoch of Reionization
- The 21cm bispectrum as a probe of non-Gaussianities due to X-ray heating
- Statistics of the epoch of reionization (EoR) 21-cm signal -- II. The evolution of the power spectrum error-covariance
- The 21cm bispectrum during reionization: a tracer of the ionization topology
- The effect of non-Gaussianity on error predictions for the Epoch of Reionization (EoR) 21-cm power spectrum
- Constraining the state of the intergalactic medium during the Epoch of Reionization using MWA 21-cm signal observations
- Constraining the EoR model parameters with the 21cm bispectrum
- Evaluating machine learning techniques for predicting power spectra from reionization simulations
- Observations of the Lyman series forest towards the redshift 7.1 quasar ULAS J1120+0641
- Sensitivity for 21cm Bispectrum from Epoch of Reionization
- Quantifying the Redshift Space Distortion of the Bispectrum I: Primordial Non-Gaussianity
- Machine learning astrophysics from 21 cm lightcones: impact of network architectures and signal contamination
- HI Fluctuations at Large Redshifts: III - Simulating the Signal Expected at GMRT
- Redshifted 21-cm Bispectrum I: Impact of the Redshift Space Distortions on the Signal from the Epoch of Reionization
- Implicit Likelihood Inference of Reionization Parameters from the 21 cm Power Spectrum
- Exploring the likelihood of the 21-cm power spectrum with simulation-based inference
- Redshifted 21-cm bispectrum II: Impact of the spin temperature fluctuations and redshift space distortions on the signal from the Cosmic Dawn
- 21cmEMU: an emulator of 21cmFAST summary observables
- Improving constraints on the reionization parameters using 21-cm bispectrum
- The Evolution of the Ultraluminous Ly-alpha Luminosity Function over z=5.7-6.6
- Deeper multi-redshift upper limits on the Epoch of Reionization 21-cm signal power spectrum from LOFAR between z=8.3 and z=10.1
- The Epoch of Reionization 21-cm Bispectrum: The impact of light-cone effects and detectability
- Inferring Astrophysics and Dark Matter Properties from 21cm Tomography using Deep Learning
- Extracting the 21-cm Power Spectrum and the reionization parameters from mock datasets using Artificial Neural Networks
- How informative are summaries of the cosmic 21-cm signal?
- Investigating X-ray sources during the epoch of reionization with the 21 cm signal
- Constraining the Reionization History using Bayesian Normalizing Flows
- Observing the Reionization : Effect of Calibration and Position Errors on Realistic Observation Conditions
- Constraints on the state of the IGM at using redshifted 21-cm observations with LOFAR
- Extracting the Global 21-cm signal from Cosmic Dawn and Epoch of Reionization in the presence of Foreground and Ionosphere
- 21cm Global Signal Extraction: Extracting the 21cm Global Signal using Artificial Neural Networks
- Emulation of the Cosmic Dawn 21-cm Power Spectrum and Classification of Excess Radio Models Using an Artificial Neural Network
- Redshifted 21-cm bispectrum: Impact of the source models on the signal and the IGM physics from the Cosmic Dawn
- Optimal, fast, and robust inference of reionization-era cosmology with the 21cmPIE-INN
- The 21-cm bispectrum from neutral hydrogen islands at z < 6
- First upper limits on the 21-cm signal power spectrum of neutral hydrogen at from the LOFAR 3C196 field
- SKATR: A Self-Supervised Summary Transformer for SKA
- Impact of the Epoch of Reionization sources on the 21-cm bispectrum
- Impact of astrophysical scatter on the Epoch of Reionization [H I] bispectrum
- Comparison of Bayesian inference methods using the Loreli II database of hydro-radiative simulations of the 21-cm signal