A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs
This provides a computationally efficient method for astrophysicists studying reionisation to generate and infer parameters from 21cm tomography data, though it is incremental as it applies an existing GAN variant to a specific domain.
The authors tackled the problem of generating realistic 21cm brightness temperature signals from the Epoch of Reionisation by using a Progressively Growing GAN to produce images covering a continuous parameter space, achieving sample generation at ~3' resolution in a second on a laptop CPU with good agreement to training data in global signal, power spectrum, and pixel distribution.
Creating a database of 21cm brightness temperature signals from the Epoch of Reionisation (EoR) for an array of reionisation histories is a complex and computationally expensive task, given the range of astrophysical processes involved and the possibly high-dimensional parameter space that is to be probed. We utilise a specific type of neural network, a Progressively Growing Generative Adversarial Network (PGGAN), to produce realistic tomography images of the 21cm brightness temperature during the EoR, covering a continuous three-dimensional parameter space that models varying X-ray emissivity, Lyman band emissivity, and ratio between hard and soft X-rays. The GPU-trained network generates new samples at a resolution of $\sim 3'$ in a second (on a laptop CPU), and the resulting global 21cm signal, power spectrum, and pixel distribution function agree well with those of the training data, taken from the 21SSD catalogue \citep{Semelin2017}. Finally, we showcase how a trained PGGAN can be leveraged for the converse task of inferring parameters from 21cm tomography samples via Approximate Bayesian Computation.