Deep learning-driven likelihood-free parameter inference for 21-cm forest observations

Tian-Yang Sun, Yue Shao, Yichao Li, Yidong Xu, He Wang, Xin Zhang

Abstract: The hyperfine structure absorption lines of neutral hydrogen in high-redshift radio spectra, known as the 21-cm forest, have been demonstrated through simulations as a powerful probe of small-scale structures governed by dark matter (DM) properties and the thermal history of intergalactic medium (IGM). By measuring the one-dimensional power spectrum of the 21-cm forest, parameter degeneracies can be broken, offering key constraints on the properties of both DM and IGM. However, conventional methods are hindered by computationally expensive simulations and a non-Gaussian likelihood function. To overcome these challenges, we propose a deep learning approach that combines generative normalizing flows for data augmentation and inference normalizing flows for parameter estimation, enabling accurate results from minimally simulated datasets. Using mock data from the Square Kilometre Array, we demonstrate the capability of this deep learning-driven approach to generating posterior distributions, providing a robust tool for probing DM and the cosmic heating history. The 21-cm forest is a powerful probe for exploring the small-scale structures in the early universe. In this work, the authors use deep learning-driven likelihood-free parameter inference to quickly and accurately estimate parameters from minimally simulated datasets, while addressing the challenge of non-Gaussian likelihood function

External IDs:doi:10.1038/s42005-025-02139-5