CLEANing Cygnus A deep and fast with R2D2

TL;DR

This paper introduces R2D2, a deep learning-based imaging method for radio interferometry that achieves high-precision, high-resolution images of Cygnus A faster than traditional algorithms like CLEAN, uSARA, and AIRI.

Contribution

The paper presents the first real-data demonstration of R2D2, a learned CLEAN-like algorithm that delivers superior resolution and speed in radio astronomy imaging.

Findings

R2D2 outperforms CLEAN in resolution and speed.

R2D2 matches the precision of uSARA and AIRI.

R2D2 requires fewer iterations, enabling faster imaging.

Abstract

A novel deep learning paradigm for synthesis imaging by radio interferometry in astronomy was recently proposed, dubbed "Residual-to-Residual DNN series for high-Dynamic range imaging" (R2D2). In this work, we start by shedding light on R2D2's algorithmic structure, interpreting it as a learned version of CLEAN with minor cycles substituted with a deep neural network (DNN) whose training is iteration-specific. We then proceed with R2D2's first demonstration on real data, for monochromatic intensity imaging of the radio galaxy Cygnus A from S band observations with the Very Large Array (VLA). We show that the modeling power of R2D2's learning approach enables delivering high-precision imaging, superseding the resolution of CLEAN, and matching the precision of modern optimization and plug-and-play algorithms, respectively uSARA and AIRI. Requiring few major-cycle iterations only, R2D2 provides a much faster reconstruction than uSARA and AIRI, known to be highly iterative, and is at least as fast as CLEAN.