DeepSource: Point Source Detection using Deep Learning

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.

arXiv comment15 pages, 13 figures, submitted to MNRAS

References in corpus (15)

• Deep Learning in Neural Networks: An Overview
• Deep Residual Learning for Image Recognition
• Astrophysics Source Code Library
• WSClean: an implementation of a fast, generic wide-field imager for radio astronomy
• Star-galaxy Classification Using Deep Convolutional Neural Networks
• Photometric Supernova Classification With Machine Learning
• The MeqTrees software system and its use for third-generation calibration of radio interferometers
• Radio Galaxy Zoo: ClaRAN - A Deep Learning Classifier for Radio Morphologies
• The ASKAP/EMU Source Finding Data Challenge
• An Australia telescope survey for CMB anisotropies
• A 325-MHz GMRT survey of the Herschel-ATLAS/GAMA fields
• Bayesian Inference for Radio Observations
• PySE: Software for Extracting Sources from Radio Images
• Unsupervised feature-learning for galaxy SEDs with denoising autoencoders
• Nonparametric Transient Classification using Adaptive Wavelets

Cited by in corpus (30)

• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• Unsupervised star, galaxy, qso classification: Application of HDBSCAN
• Square Kilometre Array Science Data Challenge 1: analysis and results
• CNN Architecture Comparison for Radio Galaxy Classification
• Separating the EoR Signal with a Convolutional Denoising Autoencoder: A Deep-learning-based Method
• Deep Learning improves identification of Radio Frequency Interference
• SILVERRUSH X: Machine Learning-Aided Selection of $9318$ LAEs at $z=2.2$, $3.3$, $4.9$, $5.7$, $6.6$, and $7.0$ from the HSC SSP and CHORUS Survey Data
• SKA Science Data Challenge 2: analysis and results
• MeerCRAB: MeerLICHT Classification of Real and Bogus Transients using Deep Learning
• Identification of point sources in gamma rays using U-shaped convolutional neural networks and a data challenge
• A machine learning classifier for LOFAR radio galaxy cross-matching techniques
• Radio astronomical images object detection and segmentation: A benchmark on deep learning methods
• YOLO-CIANNA: Galaxy detection with deep learning in radio data. I. A new YOLO-inspired source detection method applied to the SKAO SDC1
• DECORAS: detection and characterization of radio-astronomical sources using deep learning
• Radio Sources Segmentation and Classification with Deep Learning
• Morphology-assisted galaxy mass-to-light predictions using deep learning
• Deep Transfer Learning for Classification of Variable Sources
• The PAU Survey: Background light estimation with deep learning techniques
• 3D Detection and Characterisation of ALMA Sources through Deep Learning
• Challenging interferometric imaging: Machine learning-based source localization from uv-plane observations
• Hydra II: Characterisation of Aegean, Caesar, ProFound, PyBDSF, and Selavy source finders
• Deep learning-based deconvolution for interferometric radio transient reconstruction
• Self-Supervised Learning on MeerKAT Wide-Field Continuum Images
• Inpainting via Generative Adversarial Networks for CMB data analysis
• Point Proposal Network: Accelerating Point Source Detection Through Deep Learning
• ConvoSource: Radio-Astronomical Source-Finding with Convolutional Neural Networks
• Latent-space Field Tension for Astrophysical Component Detection An application to X-ray imaging
• Predicting large scale cosmological structure evolution with generative adversarial network-based autoencoders
• A comprehensive analysis using 9 dark matter halo models on the spiral galaxy NGC 4321
• Transformer-Based Source Detection and Morphological Classification in LOFAR Deep-Field Continuum Images