3D Detection of ALMA Sources Through Deep Learning

We present a Deep Learning pipeline for the detection of astronomical sources within radiointerferometric simulated data cubes. Our pipeline is constituted by two Deep Learning models: a Convolutional Autoencoder for the detection of sources within the spatial domain of the cube, and a RNN for the denoising and detection of emission peaks in the frequency domain. The combination of spatial and frequency information allows for higher completeness and helps to remove false positives. The pipeline has been tested on simulated ALMA observations achieving better performances and faster execution times with respect to traditional methods. The pipeline can detect 92% of sources up to a flux of 1.31 Jy/beam with no false positives thus providing a reliable source detection solution for future astronomical radio surveys.

Automated summary

We propose a Deep Learning pipeline for detecting astronomical sources in radiointerferometric simulated data cubes. The pipeline consists of two Deep Learning models: a Convolutional Autoencoder for spatial detection of sources, and a RNN for denoising and detecting emission peaks in the frequency domain. By combining spatial and frequency information, the pipeline achieves higher completeness and eliminates false positives. It performs better and has faster execution times compared to traditional methods, detecting 92% of sources up to 1.31 Jy/beam flux with no false positives, making it a reliable solution for future astronomical radio surveys.