Deep Learning-based Imaging in Radio Interferometry

Abstract

The sparse layouts of radio interferometers result in an incomplete sampling of the sky in Fourier space which leads to artifacts in the reconstructed images. Cleaning these systematic effects is essential for the scientific use of radiointerferometric images. Established reconstruction methods are often time-consuming, require expert-knowledge, and suffer from a lack of reproducibility. We have developed a prototype Deep Learning-based method that generates reproducible images in an expedient fashion. To this end, we take advantage of the efficiency of Convolutional Neural Networks to reconstruct image data from incomplete information in Fourier space. The Neural Network architecture is inspired by super-resolution models that utilize residual blocks. Using simulated data of radio galaxies that are composed of Gaussian components we train Deep Learning models whose reconstruction capability is quantified using various measures. The reconstruction performance is evaluated on clean and noisy input data by comparing the resulting predictions with the true source images. We find that source angles and sizes are well reproduced, while the recovered fluxes show substantial scatter, albeit not worse than existing methods without fine-tuning. Finally, we propose more advanced approaches using Deep Learning that include uncertainty estimates and a concept to analyze larger images.

Accepted for publication in Astronomy & Astrophysics

References in corpus (4)

• scikit-image: Image processing in Python
• WSClean: an implementation of a fast, generic wide-field imager for radio astronomy
• Revisiting the radio interferometer measurement equation. I. A full-sky Jones formalism
• MOJAVE. XVII. Jet Kinematics and Parent Population Properties of Relativistically Beamed Radio-Loud Blazars

Cited by in corpus (16)

• Deep learning-based radiointerferometric imaging with GAN-aided training
• Morphological Classification of Radio Galaxies with wGAN-supported Augmentation
• 3D Detection and Characterisation of ALMA Sources through Deep Learning
• Challenging interferometric imaging: Machine learning-based source localization from uv-plane observations
• fast-resolve: Fast Bayesian Radio Interferometric Imaging
• Radio-astronomical Image Reconstruction with Conditional Denoising Diffusion Model
• Deep learning-based deconvolution for interferometric radio transient reconstruction
• Deep learning inference with the Event Horizon Telescope II. The Zingularity framework for Bayesian artificial neural networks
• PolyCLEAN: Atomic Optimization for Super-Resolution Imaging and Uncertainty Estimation in Radio Interferometry
• How to make CLEAN variants faster? Using clustered components informed by the autocorrelation function
• Application of Physics-Informed Neural Networks in Removing Telescope Beam Effects
• Semi-Supervised Rotation Measure Deconvolution and its application to MeerKAT observations of galaxy clusters
• A Decentralized Framework for Radio-interferometric Image Reconstruction
• BIPP: An efficient HPC implementation of the Bluebild algorithm for radio astronomy
• Very-Long Baseline Interferometry Imaging with Closure Invariants using Conditional Image Diffusion
• An Unsupervised Learning Method for Radio Interferometry Deconvolution