Comparing sampling techniques to chart parameter space of 21 cm Global signal with Artificial Neural Networks

Abstract

Understanding the first billion years of the universe requires studying two critical epochs: the Epoch of Reionization (EoR) and Cosmic Dawn (CD). However, due to limited data, the properties of the Intergalactic Medium (IGM) during these periods remain poorly understood, leading to a vast parameter space for the global 21cm signal. Training an Artificial Neural Network (ANN) with a narrowly defined parameter space can result in biased inferences. To mitigate this, the training dataset must be uniformly drawn from the entire parameter space to cover all possible signal realizations. However, drawing all possible realizations is computationally challenging, necessitating the sampling of a representative subset of this space. This study aims to identify optimal sampling techniques for the extensive dimensionality and volume of the 21cm signal parameter space. The optimally sampled training set will be used to train the ANN to infer from the global signal experiment. We investigate three sampling techniques: random, Latin hypercube (stratified), and Hammersley sequence (quasi-Monte Carlo) sampling, and compare their outcomes. Our findings reveal that sufficient samples must be drawn for robust and accurate ANN model training, regardless of the sampling technique employed. The required sample size depends primarily on two factors: the complexity of the data and the number of free parameters. More free parameters necessitate drawing more realizations. Among the sampling techniques utilized, we find that ANN models trained with Hammersley sequence sampling demonstrate greater robustness compared to those trained with Latin hypercube and Random sampling.

31 pages, 17 figures, comments are welcome, Published in JCAP

References in corpus (39)

• LOFAR: The LOw-Frequency ARray
• Cosmology at Low Frequencies: The 21 cm Transition and the High-Redshift Universe
• An absorption profile centred at 78 megahertz in the sky-averaged spectrum
• 21-cm cosmology
• Observational constraints on Cosmic Reionization
• Hydrogen Epoch of Reionization Array (HERA)
• Reionization and Cosmology with 21 cm Fluctuations
• 21CMMC: an MCMC analysis tool enabling astrophysical parameter studies of the cosmic 21 cm signal
• Charting the Parameter Space of the Global 21-cm Signal
• Design and characterization of the Large-Aperture Experiment to Detect the Dark Age (LEDA) radiometer systems
• The Cosmic Dawn and Epoch of Reionization with the Square Kilometre Array
• An Improved Method for 21cm Foreground Removal
• The redshifted 21-cm signal in the EDGES low-band spectrum
• The Epoch of Reionization
• Exploring multi-dimensional spaces: a Comparison of Latin Hypercube and Quasi Monte Carlo Sampling Techniques
• Decoding the X-ray Properties of Pre-Reionization Era Sources
• Emulation of reionization simulations for Bayesian inference of astrophysics parameters using neural networks
• Emulating the Global 21-cm Signal from Cosmic Dawn and Reionization
• Simulation-Based Inference of Reionization Parameters From 3D Tomographic 21 cm Lightcone Images
• Bayesian emulator optimisation for cosmology: application to the Lyman-alpha forest
• An MCMC approach to extracting the global 21-cm signal during the cosmic dawn from sky-averaged radio observations
• maxsmooth: Rapid Maximally Smooth Function Fitting With Applications in Global 21-cm Cosmology
• Evaluating machine learning techniques for predicting power spectra from reionization simulations
• GLOBALEMU: A novel and robust approach for emulating the sky-averaged 21-cm signal from the cosmic dawn and epoch of reionisation
• Ruling out 3 keV warm dark matter using 21 cm-EDGES data
• 21SSD: a public database of simulated 21-cm signals from the epoch of reionization
• Implicit Likelihood Inference of Reionization Parameters from the 21 cm Power Spectrum
• Global 21-cm Signal Extraction from Foreground and Instrumental Effects II: Efficient and Self-Consistent Technique for Constraining Nonlinear Signal Models
• Parametrizations of the global 21-cm signal and parameter estimation from single-dipole experiments
• Exploring the likelihood of the 21-cm power spectrum with simulation-based inference
• Improving constraints on the reionization parameters using 21-cm bispectrum
• 21cmVAE: A Very Accurate Emulator of the 21-cm Global Signal
• Constraining the X-ray heating and reionization using 21-cm power spectra with Marginal Neural Ratio Estimation
• Global 21-cm signal extraction from foreground and instrumental effects IV: Accounting for realistic instrument uncertainties and their overlap with foreground and signal models
• Selection between foreground models for global 21-cm experiments
• Extracting the 21-cm Power Spectrum and the reionization parameters from mock datasets using Artificial Neural Networks
• Using Artificial Neural Networks to extract the 21-cm Global Signal from the EDGES data
• 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

Cited by in corpus (2)

• Impact of Calibration and Position Errors on Astrophysical Parameters of the HI 21cm Signal
• Exploring Machine Learning Regression Models for Advancing Foreground Mitigation and Global 21cm Signal Parameter Extraction