In Search of global 21-cm signal using artificial neural network in light of EDGES and ARCADE 2

Abstract

Understanding the astrophysical nature of the first stars still remains an unsolved problem in cosmology. The redshifted global 21-cm signal and power spectrum act as a treasure trove to probe the Cosmic Dawn era -- when the intergalactic medium was mostly neutral. Many experiments, like SARAS 3, SKA, EDGES, DARE, etc., have been proposed to probe the cosmic dawn era. However, extracting the faint cosmological signal buried inside the brighter foregrounds O(104) remains challenging. Considering the excess radio background, we have constructed all possible T21 signals in the EDGES limit. We have used a single Artificial Neural Network for T21 parameter extraction in the presence of the foreground and noise with Root Mean Square Error (RMSE) and R-Squared (R2) score of (0.2?0.08) and (0.66?0.94), respectively. Here, we also explore the parameter estimation in the presence of heating of intergalactic medium due to background radio radiation mediated by Ly? photons from first stars, and we found that the effect indeed has a significant impact on parameters correlation and their estimation.