Reconstruction of Reionization Histories from 21 cm Power-Spectrum Evolution with Artificial Neural Networks

TL;DR

This study demonstrates that neural networks can effectively reconstruct cosmic reionization histories from the evolution of the 21 cm power spectrum, with high accuracy for key timing parameters, even under realistic noise conditions.

Contribution

The paper introduces a neural network approach to invert 21 cm power spectrum data for reionization history reconstruction, highlighting its accuracy and robustness.

Findings

Midpoint redshift $z_{50}$ is reconstructed with MAE = 0.0046.

Reconstruction remains stable under SKA1-Low-like noise.

Fixed-$k$ power spectrum evolution encodes strong timing information.

Abstract

We investigate whether the redshift evolution of the fixed-$k$ dimensionless 21 cm power spectrum, $\Delta^2_{21}(k, z)$, contains sufficient information to reconstruct reionization histories $x_{\mathrm{HI}}(z)$ with artificial neural networks. Using semi-numerical realizations generated within a restricted three-parameter 21cmFAST model family, we train a compact feed-forward network to learn the inverse mapping from power-spectrum trajectories to the neutral-fraction history over $6 \le z \le 15$. For $k = 0.1$, $0.5$, and $1.0\ h\ \mathrm{Mpc}^{-1}$, representative tests on an independent test set show that the midpoint redshift $z_{50}$ is recovered more accurately than the duration $\Delta z = z_{75} - z_{25}$: $z_{50}$ is reconstructed with MAE = 0.0046 and RMSE = 0.0100, whereas $\Delta z$ yields MAE = 0.0302 and RMSE = 0.0378. This result indicates that fixed-$k$ power-spectrum evolution carries stronger information about the timing of reionization than about the detailed width of the transition within the adopted prior. We further test an idealized foreground-free SKA1-Low-like thermal-plus-sample-variance noise model and find that the reconstruction remains stable in the favorable signal-to-noise regime considered here. These results demonstrate that neural networks can serve as prior-dependent inverse mapping for reconstructing reionization histories from 21 cm power-spectrum evolution.