DeepSource: Point Source Detection using Deep Learning

TL;DR

DeepSource employs convolutional neural networks to significantly improve point source detection in radio astronomy images, outperforming traditional methods like PyBDSF in purity and completeness, especially at low SNR levels.

Contribution

This paper introduces DeepSource, a novel deep learning-based method that enhances source detection accuracy in radio interferometry images, outperforming existing algorithms.

Findings

DeepSource achieves near-perfect purity and completeness at SNR=4.

It outperforms PyBDSF in all metrics across simulated MeerKAT images.

DeepSource can learn to balance purity and completeness for different science goals.

Abstract

Point source detection at low signal-to-noise is challenging for astronomical surveys, particularly in radio interferometry images where the noise is correlated. Machine learning is a promising solution, allowing the development of algorithms tailored to specific telescope arrays and science cases. We present DeepSource - a deep learning solution - that uses convolutional neural networks to achieve these goals. DeepSource enhances the Signal-to-Noise Ratio (SNR) of the original map and then uses dynamic blob detection to detect sources. Trained and tested on two sets of 500 simulated 1 deg x 1 deg MeerKAT images with a total of 300,000 sources, DeepSource is essentially perfect in both purity and completeness down to SNR = 4 and outperforms PyBDSF in all metrics. For uniformly-weighted images it achieves a Purity x Completeness (PC) score at SNR = 3 of 0.73, compared to 0.31 for the best PyBDSF model. For natural-weighting we find a smaller improvement of ~40% in the PC score at SNR = 3. If instead we ask where either of the purity or completeness first drop to 90%, we find that DeepSource reaches this value at SNR = 3.6 compared to the 4.3 of PyBDSF (natural-weighting). A key advantage of DeepSource is that it can learn to optimally trade off purity and completeness for any science case under consideration. Our results show that deep learning is a promising approach to point source detection in astronomical images.