Structured Variational Inference for Simulating Populations of Radio Galaxies

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.

20 pages, 20 figures, accepted MNRAS

References in corpus (18)

• Going Deeper with Convolutions
• GaLactic and Extragalactic All-sky Murchison Widefield Array (GLEAM) survey I: A low-frequency extragalactic catalogue
• Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro
• CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms
• Revisiting the Fanaroff-Riley dichotomy and radio-galaxy morphology with the LOFAR Two-Metre Sky Survey (LoTSS)
• Classifying Radio Galaxies with Convolutional Neural Network
• Luminosity function, sizes and FR dichotomy of radio-loud AGN
• FRICAT: A FIRST catalog of FRI radio galaxies
• Simulation of Astronomical Images from Optical Survey Telescopes using a Comprehensive Photon Monte Carlo Approach
• The MeerKAT International GHz Tiered Extragalactic Exploration (MIGHTEE) Survey
• Morphological classification of radio galaxies: Capsule Networks versus Convolutional Neural Networks
• 3D Relativistic MHD numerical simulations of X-shaped radio sources
• The Combined NVSS-FIRST Galaxies (CoNFIG) Sample - I. Sample Definition, Classification and Evolution
• Preventing Posterior Collapse with delta-VAEs
• Accelerated Discovery of Sustainable Building Materials
• VAE/WGAN-Based Image Representation Learning For Pose-Preserving Seamless Identity Replacement In Facial Images
• CDVAE: Co-embedding Deep Variational Auto Encoder for Conditional Variational Generation
• Morphological classification of radio sources for galaxy evolution and cosmology with SKA-MID

Cited by in corpus (3)

• Quantifying Uncertainty in Deep Learning Approaches to Radio Galaxy Classification
• Investigation of stellar magnetic activity using variational autoencoder based on low-resolution spectroscopic survey
• Radio Galaxy Zoo: Using semi-supervised learning to leverage large unlabelled data-sets for radio galaxy classification under data-set shift