Convolutional Deep Denoising Autoencoders for Radio Astronomical Images

Abstract

We apply a Machine Learning technique known as Convolutional Denoising Autoencoder to denoise synthetic images of state-of-the-art radio telescopes, with the goal of detecting the faint, diffused radio sources predicted to characterise the radio cosmic web. In our application, denoising is intended to address both the reduction of random instrumental noise and the minimisation of additional spurious artefacts like the sidelobes, resulting from the aperture synthesis technique. The effectiveness and the accuracy of the method are analysed for different kinds of corrupted input images, together with its computational performance. Specific attention has been devoted to create realistic mock observations for the training, exploiting the outcomes of cosmological numerical simulations, to generate images corresponding to LOFAR HBA 8 hours observations at 150 MHz. Our autoencoder can effectively denoise complex images identifying and extracting faint objects at the limits of the instrumental sensitivity. The method can efficiently scale on large datasets, exploiting high performance computing solutions, in a fully automated way (i.e. no human supervision is required after training). It can accurately perform image segmentation, identifying low brightness outskirts of diffused sources, proving to be a viable solution for detecting challenging extended objects hidden in noisy radio observations.

21 pages, 14 figures, Accepted for publication by MNRAS

References in corpus (19)

• WSClean: an implementation of a fast, generic wide-field imager for radio astronomy
• An optimized algorithm for multi-scale wideband deconvolution of radio astronomical images
• Revisiting the radio interferometer measurement equation. I. A full-sky Jones formalism
• SoFiA: a flexible source finder for 3D spectral line data
• Radio signature of cosmological structure formation shocks
• A radio ridge connecting two galaxy clusters in a filament of the cosmic web
• Revisiting the radio interferometer measurement equation. II. Calibration and direction-dependent effects
• The Abell 3391/95 galaxy cluster system: A 15 Mpc intergalactic medium emission filament, a warm gas bridge, infalling matter clumps, and (re-) accelerated plasma discovered by combining SRG/eROSITA data with ASKAP/EMU and DECam data
• MORESANE: MOdel REconstruction by Synthesis-ANalysis Estimators. A sparse deconvolution algorithm for radio interferometric imaging
• The Coma cluster at LOFAR frequencies I: insights into particle acceleration mechanisms in the radio bridge
• On the population of remnant FRII radio galaxies and implications for radio source dynamics
• Searching for changing-state AGNs in massive datasets -- I: applying deep learning and anomaly detection techniques to find AGNs with anomalous variability behaviours
• Revived Fossil Plasma Sources in Galaxy Clusters
• Unveiling the rarest morphologies of the LOFAR Two-metre Sky Survey radio source population with self-organised maps
• Detecting shocked intergalactic gas with X-ray and radio observations
• A giant radio bridge connecting two clusters in Abell 1758
• VLA resolves unexpected radio structures in the Perseus cluster of galaxies
• Multi wavelength cross-correlation analysis of the simulated cosmic web
• Deep Transfer Learning for Classification of Variable Sources