| Name: Anoop Krishna |
| Affiliation: National Institute of Technology, Calicut |
| Conference ID: ASI2026_87 |
| Title: Improving 21-cm Signal Inference with Machine Learning and Higher-Order Statistics |
| Abstract Type: Poster |
| Abstract Category: Galaxies and Cosmology |
| Author(s) and Co-Author(s) with Affiliation: Anoop Krishna(National Institute of Technology, Calicut -673601, India), Deepthi Moorkanat(National Institute of Technology, Calicut -673601, India), Hiten Hiten(National Institute of Technology, Calicut -673601, India), Rajesh Mondal(National Institute of Technology, Calicut -673601, India) |
| Abstract: The redshifted 21-cm emission from neutral hydrogen (HI)provides a powerful window into the early universe, particularly the Cosmic, Dark Ages and the Epoch of Reionization (EoR). Detecting this signal is highly challenging, as it is both extremely weak and strongly obscured by foreground radiation from bright astrophysical sources. To address these difficulties, one typically relies on the statistical properties of the 21-cm fluctuations to extract astrophysical and cosmological information. In this work, we make use of machine learning methods to efficiently generate large ensembles of simulations and employ Markov Chain Monte Carlo (MCMC) techniques to constrain the evolution of the neutral hydrogen fraction. Although much of the existing work has been limited to the power spectrum as a first-order statistic, this approach does not capture the full information contained in the signal. By extending the analysis to higher-order measures such as the bispectrum, we demonstrate improved accuracy in parameter estimation and gain a more comprehensive understanding of the reionization process. |
