Removing Astrophysics in 21 cm maps with Neural Networks

TL;DR

This paper develops a neural network method to remove astrophysical effects from 21 cm maps, enabling the extraction of underlying matter fields and astrophysical parameters, which enhances the analysis of high-redshift Universe signals.

Contribution

It introduces a convolutional neural network trained on simulated data to effectively separate astrophysical influences from 21 cm maps, improving the accuracy of matter field reconstruction and parameter constraints.

Findings

Neural network accurately reconstructs matter fields from 21 cm maps.

Statistical properties of reconstructed maps match true ones within a few percent.

Saliency maps reveal features used for astrophysical parameter estimation.

Abstract

Measuring temperature fluctuations in the 21 cm signal from the Epoch of Reionization and the Cosmic Dawn is one of the most promising ways to study the Universe at high redshifts. Unfortunately, the 21 cm signal is affected by both cosmology and astrophysics processes in a non-trivial manner. We run a suite of 1,000 numerical simulations with different values of the main astrophysical parameters. From these simulations we produce tens of thousands of 21 cm maps at redshifts $10\leq z\leq 20$. We train a convolutional neural network to remove the effects of astrophysics from the 21 cm maps, and output maps of the underlying matter field. We show that our model is able to generate 2D matter fields that not only resemble the true ones visually, but whose statistical properties agree with the true ones within a few percent down to pretty small scales. We demonstrate that our neural network retains astrophysical information, that can be used to constrain the value of the astrophysical parameters. Finally, we use saliency maps to try to understand which features of the 21 cm maps is the network using in order to determine the value of the astrophysical parameters.