Learned radio interferometric imaging for varying visibility coverage

TL;DR

This paper introduces learned reconstruction methods for radio interferometry that adapt to varying visibility coverages, reducing the need for retraining and improving generalization to different observation conditions.

Contribution

The authors develop unrolled iterative reconstruction techniques that incorporate measurement operators, enabling coverage-agnostic radio image reconstruction with minimal fine-tuning.

Findings

Unrolled iterative methods generalize well across different visibility coverages.

These methods outperform learned post-processing in terms of flexibility and reconstruction quality.

They are effective on realistic radio observations with high dynamic range.

Abstract

With the next generation of interferometric telescopes, such as the Square Kilometre Array (SKA), the need for highly computationally efficient reconstruction techniques is particularly acute. The challenge in designing learned, data-driven reconstruction techniques for radio interferometry is that they need to be agnostic to the varying visibility coverages of the telescope, since these are different for each observation. Because of this, learned post-processing or learned unrolled iterative reconstruction methods must typically be retrained for each specific observation, amounting to a large computational overhead. In this work we develop learned post-processing and unrolled iterative methods for varying visibility coverages, proposing training strategies to make these methods agnostic to variations in visibility coverage with minimal to no fine-tuning. Learned post-processing techniques are heavily dependent on the prior information encoded in training data and generalise poorly to other visibility coverages. In contrast, unrolled iterative methods, which include the telescope measurement operator inside the network, achieve good reconstruction quality and computation time, generalising well to other coverages and require little to no fine-tuning. Furthermore, they generalise well to more realistic radio observations and are able to reconstruct images with with a larger dynamic range than the training set.