DECORAS: detection and characterization of radio-astronomical sources using deep learning

TL;DR

DECORAS is a deep learning approach that efficiently detects and characterizes radio sources in VLBI images, outperforming traditional methods in completeness and reliability, and is suitable for future wide-field surveys.

Contribution

This paper introduces DECORAS, a scalable deep learning model for source detection and characterization directly from VLBI visibility data, without prior deconvolution.

Findings

DECORAS achieves higher completeness and purity than traditional algorithms.

It reliably recovers source positions within 0.61 mas.

It accurately estimates source size and brightness for most sources.

Abstract

We present DECORAS, a deep learning based approach to detect both point and extended sources from Very Long Baseline Interferometry (VLBI) observations. Our approach is based on an encoder-decoder neural network architecture that uses a low number of convolutional layers to provide a scalable solution for source detection. In addition, DECORAS performs source characterization in terms of the position, effective radius and peak brightness of the detected sources. We have trained and tested the network with images that are based on realistic Very Long Baseline Array (VLBA) observations at 20 cm. Also, these images have not gone through any prior de-convolution step and are directly related to the visibility data via a Fourier transform. We find that the source catalog generated by DECORAS has a better overall completeness and purity, when compared to a traditional source detection algorithm. DECORAS is complete at the 7.5$\sigma$ level, and has an almost factor of two improvement in reliability at 5.5$\sigma$. We find that DECORAS can recover the position of the detected sources to within 0.61 $\pm$ 0.69 mas, and the effective radius and peak surface brightness are recovered to within 20 per cent for 98 and 94 per cent of the sources, respectively. Overall, we find that DECORAS provides a reliable source detection and characterization solution for future wide-field VLBI surveys.