A comparative study of source-finding techniques in HI emission line cubes using SoFiA, MTObjects, and supervised deep learning

TL;DR

This study compares traditional, machine learning, and deep learning techniques for detecting HI sources in 3D spectral line data cubes, finding that combining SoFiA with a classifier yields the best results.

Contribution

It introduces a pipeline integrating traditional and deep learning methods for HI source detection, highlighting the potential of supervised deep learning with improved training data.

Findings

SoFiA with a random forest classifier achieved the best detection performance.

Deep learning approach (V-Net) shows promise but needs better training data.

Combining classical and machine learning methods enhances source detection accuracy.

Abstract

The 21 cm spectral line emission of atomic neutral hydrogen (HI) is one of the primary wavelengths observed in radio astronomy. However, the signal is intrinsically faint and the HI content of galaxies depends on the cosmic environment, requiring large survey volumes and survey depth to investigate the HI Universe. As the amount of data coming from these surveys continues to increase with technological improvements, so does the need for automatic techniques for identifying and characterising HI sources while considering the tradeoff between completeness and purity. This study aimed to find the optimal pipeline for finding and masking the most sources with the best mask quality and the fewest artefacts in 3D neutral hydrogen cubes. Various existing methods were explored in an attempt to create a pipeline to optimally identify and mask the sources in 3D neutral hydrogen 21 cm spectral line data cubes. Two traditional source-finding methods were tested, SoFiA and MTObjects, as well as a new supervised deep learning approach, in which a 3D convolutional neural network architecture, known as V-Net was used. These three source-finding methods were further improved by adding a classical machine learning classifier as a post-processing step to remove false positive detections. The pipelines were tested on HI data cubes from the Westerbork Synthesis Radio Telescope with additional inserted mock galaxies. SoFiA combined with a random forest classifier provided the best results, with the V-Net-random forest combination a close second. We suspect this is due to the fact that there are many more mock sources in the training set than real sources. There is, therefore, room to improve the quality of the V-Net network with better-labelled data such that it can potentially outperform SoFiA.