Emulation of reionization simulations for Bayesian inference of astrophysics parameters using neural networks

TL;DR

This paper explores using neural networks to emulate reionization simulations, enabling faster Bayesian inference of astrophysical parameters from upcoming 21cm observations, with promising accuracy using limited training data.

Contribution

It demonstrates that neural networks can effectively emulate complex reionization models with minimal training data, improving computational efficiency for parameter inference.

Findings

Neural networks achieve good predictions with only 100 training models.

Emulation results are comparable to traditional Bayesian analysis methods.

Training duration and set size significantly influence prediction quality.

Abstract

Next generation radio experiments such as LOFAR, HERA and SKA are expected to probe the Epoch of Reionization and claim a first direct detection of the cosmic 21cm signal within the next decade. Data volumes will be enormous and can thus potentially revolutionize our understanding of the early Universe and galaxy formation. However, numerical modelling of the Epoch of Reionization can be prohibitively expensive for Bayesian parameter inference and how to optimally extract information from incoming data is currently unclear. Emulation techniques for fast model evaluations have recently been proposed as a way to bypass costly simulations. We consider the use of artificial neural networks as a blind emulation technique. We study the impact of training duration and training set size on the quality of the network prediction and the resulting best fit values of a parameter search. A direct comparison is drawn between our emulation technique and an equivalent analysis using 21CMMC. We find good predictive capabilities of our network using training sets of as low as 100 model evaluations, which is within the capabilities of fully numerical radiative transfer codes.