Simulating images of radio galaxies with diffusion models

Abstract

With increasing amounts of data in astronomy, automated analysis methods have become crucial. Synthetic data are required for developing and testing such methods. Current simulations often suffer from insufficient detail or inaccurate representation of source type occurrences. To overcome those deficiencies, we implemented a deep generative model trained on observations to generate realistic radio galaxy images with full control over the flux and source morphology. We used a diffusion model, trained with continuous time steps to reduce sampling time without quality impairments. Two models were trained on two different datasets, respectively. One set was a selection of images from the second data release of the LOFAR Two-Metre Sky Survey (LoTSS). The model is conditioned on peak flux values to preserve signal intensity information after re-scaling image pixel values. The other, smaller set was obtained from the VLA survey of Faint Images of the Radio Sky at Twenty-Centimeters (FIRST). In that set, every image was provided with a morphological class label the corresponding model was conditioned on. Conditioned sampling is realized with classifier-free diffusion guidance. We evaluated the quality of generated images by comparing distributions of different quantities over the real and generated data, including results from the standard source-finding algorithms. The class conditioning was evaluated by training a classifier and comparing its performance on both real and generated data. We were able to generate realistic images of high quality using 25 sampling steps, which is unprecedented in the field of radio astronomy. The generated images are visually indistinguishable from the training data and the distributions of different image metrics were replicated. The classifier performs equally well for real and generated images, indicating strong sampling control over morphological properties.

References in corpus (17)

• The Astropy Project: Sustaining and Growing a Community-oriented Open-source Project and the Latest Major Release (v5.0) of the Core Package
• The LOFAR Two-metre Sky Survey - I. Survey Description and Preliminary Data Release
• The LOFAR Two-metre Sky Survey -- V. Second data release
• LOFAR Sparse Image Reconstruction
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• The LOFAR Two-Metre Sky Survey (LoTSS): VI. Optical identifications for the second data release
• Square Kilometre Array Science Data Challenge 1: analysis and results
• Deep Learning Assisted Data Inspection for Radio Astronomy
• The angular two-point correlation of NVSS galaxies revisited
• Deep reinforcement learning for smart calibration of radio telescopes
• Investigating ionospheric calibration for LOFAR 2.0 with simulated observations
• Structured Variational Inference for Simulating Populations of Radio Galaxies
• Deep learning-based radiointerferometric imaging with GAN-aided training
• Morphological Classification of Radio Galaxies with wGAN-supported Augmentation
• Radio-astronomical Image Reconstruction with Conditional Denoising Diffusion Model
• Hydra II: Characterisation of Aegean, Caesar, ProFound, PyBDSF, and Selavy source finders
• Hydra I: An extensible multi-source-finder comparison and cataloguing tool

Cited by in corpus (1)

• Can AI Dream of Unseen Galaxies? Conditional Diffusion Model for Galaxy Morphology Augmentation