Structured Variational Inference for Simulating Populations of Radio Galaxies

Tools

Bastien, David J. and Scaife, Anna M. M. and Tang, Hongming and Bowles, Micah and Porter, Fiona (2021) Structured Variational Inference for Simulating Populations of Radio Galaxies. Monthly Notices of the Royal Astronomical Society, 503 (3). pp. 3351-3370. ISSN 0035-8711 (https://doi.org/10.1093/mnras/stab588)

[thumbnail of Structured Variational Inference for Simulating Populations of Radio Galaxies]
Preview
 Text. Filename: 2102.01007v2.pdf
Preprint
License: Creative Commons Attribution 4.0 logo
Download (4MB)| Preview

Abstract

We present a model for generating postage stamp images of synthetic Fanaroff-Riley Class I and Class II radio galaxies suitable for use in simulations of future radio surveys such as those being developed for the Square Kilometre Array. This model uses a fully-connected neural network to implement structured variational inference through a variational auto-encoder and decoder architecture. In order to optimise the dimensionality of the latent space for the auto-encoder we introduce the radio morphology inception score (RAMIS), a quantitative method for assessing the quality of generated images, and discuss in detail how data pre-processing choices can affect the value of this measure. We examine the 2-dimensional latent space of the VAEs and discuss how this can be used to control the generation of synthetic populations, whilst also cautioning how it may lead to biases when used for data augmentation.

ORCID iDs

Bastien, David J., Scaife, Anna M. M., Tang, Hongming, Bowles, Micah and Porter, Fiona ORCID logoORCID: https://orcid.org/0000-0002-5695-0633;
CORE (COnnecting REpositories)