Self-supervised contrastive learning of radio data for source detection, classification and peculiar object discovery

Abstract

New advancements in radio data post-processing are underway within the SKA precursor community, aiming to facilitate the extraction of scientific results from survey images through a semi-automated approach. Several of these developments leverage deep learning (DL) methodologies for diverse tasks, including source detection, object or morphology classification, and anomaly detection. Despite substantial progress, the full potential of these methods often remains untapped due to challenges associated with training large supervised models, particularly in the presence of small and class-unbalanced labelled datasets. Self-supervised learning has recently established itself as a powerful methodology to deal with some of the aforementioned challenges, by directly learning a lower-dimensional representation from large samples of unlabelled data. The resulting model and data representation can then be used for data inspection and various downstream tasks if a small subset of labelled data is available. In this work, we explored contrastive learning methods to learn suitable radio data representation from unlabelled images taken from the ASKAP EMU and SARAO MeerKAT GPS surveys. We evaluated trained models and the obtained data representation over smaller labelled datasets, also taken from different radio surveys, in selected analysis tasks: source detection and classification, and search for objects with peculiar morphology. For all explored downstream tasks, we reported and discussed the benefits brought by self-supervised foundational models built on radio data.

21 pages, 16 figures

References in corpus (17)

• Classifying Radio Galaxies with Convolutional Neural Network
• Radio Galaxy Zoo: Compact and extended radio source classification with deep learning
• Astronomaly: Personalised Active Anomaly Detection in Astronomical Data
• A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected From The Best-Heckman Sample
• Cataloging the radio-sky with unsupervised machine learning: a new approach for the SKA era
• Radio Galaxy Zoo: Unsupervised Clustering of Convolutionally Auto-encoded Radio-astronomical Images
• Discovery of a new extragalactic circular radio source with ASKAP: ORC J0102-2450
• Unveiling the rarest morphologies of the LOFAR Two-metre Sky Survey radio source population with self-organised maps
• A unique, ring-like radio source with quadrilateral structure detected with machine learning
• SCORPIO: A deep survey of Radio Emission from the stellar life-cycle
• Enabling Unsupervised Discovery in Astronomical Images through Self-Supervised Representations
• YOLO-CIANNA: Galaxy detection with deep learning in radio data. I. A new YOLO-inspired source detection method applied to the SKAO SDC1
• Radio source-component association for the LOFAR Two-metre Sky Survey with region-based convolutional neural networks
• Radio Sources Segmentation and Classification with Deep Learning
• Identifying anomalous radio sources in the EMU Pilot Survey using a complexity-based approach
• The VMC Survey -- XLIX. Discovery of a population of quasars dominated by nuclear dust emission behind the Magellanic Clouds
• Morphological Classification of Radio Galaxies using Semi-Supervised Group Equivariant CNNs

Cited by in corpus (4)

• Classification of Radio Sources Through Self-Supervised Learning
• Transformer-Based Source Detection and Morphological Classification in LOFAR Deep-Field Continuum Images
• Galaxy clusters in the LoTSS-DR3: Catalogues and detection pipeline for diffuse radio emission
• Radio Galaxy Zoo: Morphological classification by Fanaroff-Riley designation using self-supervised pre-training