Considerable observational efforts are being dedicated to measuring the
sky-averaged (global) 21-cm signal of neutral hydrogen from Cosmic Dawn and the
Epoch of Reionization. Deriving observational constraints on the astrophysics
of this era requires modelling tools that can quickly and accurately generate
theoretical signals across the wide astrophysical parameter space. For this
purpose artificial neural networks were used to create the only two existing
global signal emulators 21cmGEM and globalemu. In this paper we introduce
21cmVAE, a global signal emulator based on advanced machine learning methods
such as variational autoencoder (VAE) and trained with the same dataset of ~
30,000 global signals as the other two emulators. The VAE allows us to explore
a low-dimensional representation of the dataset and establish the most
important astrophysical processes that drive the global 21-cm signal at
different epochs. 21cmVAE has a relative rms error of only 0.41% —
equivalently 0.66 mK — on average, which is a significant improvement compared
to the existing emulators, and a run time of 0.04 seconds per parameter set.
The emulator, the code, and the processed datasets are publicly available at
https://github.com/christianhbye/21cmVAE and through
http://doi.org/10.5281/zenodo.5085445.
Read More