Super-resolving Herschel imaging: a proof of concept using Deep Neural Networks

Abstract

Wide-field sub-millimetre surveys have driven many major advances in galaxy evolution in the past decade, but without extensive follow-up observations the coarse angular resolution of these surveys limits the science exploitation. This has driven the development of various analytical deconvolution methods. In the last half a decade Generative Adversarial Networks have been used to attempt deconvolutions on optical data. Here we present an autoencoder with a novel loss function to overcome this problem in the sub-millimeter wavelength range. This approach is successfully demonstrated on Herschel SPIRE 500$\mu$m COSMOS data, with the super-resolving target being the JCMT SCUBA-2 450$\mu$m observations of the same field. We reproduce the JCMT SCUBA-2 images with high fidelity using this autoencoder. This is quantified through the point source fluxes and positions, the completeness and the purity.

arXiv commentPublished by MNRAS in Volume 507 issue 1 October 2021, 12 pages, 7 figures. https://doi.org/10.1093/mnras/stab2195

References in corpus (44)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Array Programming with NumPy
• Astropy: A Community Python Package for Astronomy
• The Astropy Project: Building an inclusive, open-science project and status of the v2.0 core package
• Generative Adversarial Networks
• Herschel Space Observatory - An ESA facility for far-infrared and submillimetre astronomy
• The Herschel-SPIRE instrument and its in-flight performance
• The Herschel Multi-tiered Extragalactic Survey: HerMES
• The Herschel ATLAS
• SCUBA-2: The 10000 pixel bolometer camera on the James Clerk Maxwell Telescope
• The Detection of a Population of Submillimeter-Bright, Strongly-Lensed Galaxies
• The SCUBA-2 Cosmology Legacy Survey: 850um maps, catalogues and number counts
• An ALMA survey of submillimeter galaxies in the Extended Chandra Deep Field South: Source catalog and multiplicity
• The SCUBA HAlf Degree Extragalactic Survey (SHADES) - III. Identification of radio and mid-infrared counterparts to submillimetre galaxies
• HerMES: The SPIRE confusion limit
• SCUBA-2: on-sky calibration using submillimetre standard sources
• An ALMA survey of the SCUBA-2 CLS UDS field: Physical properties of 707 Sub-millimetre Galaxies
• The SCUBA-2 Cosmology Legacy Survey: ALMA resolves the rest-frame far-infrared emission of sub-millimeter galaxies
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• HerMES: SPIRE galaxy number counts at 250, 350 and 500 microns
• Submillimetre galaxies in a hierarchical universe: number counts, redshift distribution, and implications for the IMF
• The Herschel-ATLAS Data Release 1 Paper I: Maps, Catalogues and Number Counts
• "Super-deblended" Dust Emission in Galaxies: II. Far-IR to (sub)millimeter photometry and high redshift galaxy candidates in the full COSMOS field
• Characterisation of SCUBA-2 450um and 850um-selected Galaxies in the COSMOS Field
• HerMES: Cosmic Infrared Background Anisotropies and the Clustering of Dusty Star-Forming Galaxies
• DustPedia: Multiwavelength Photometry and Imagery of 875 Nearby Galaxies in 42 Ultraviolet--Microwave Bands
• HELP: XID+, The Probabilistic De-blender for Herschel SPIRE maps
• The SCUBA-2 Cosmology Legacy Survey: blank-field number counts of 450um-selected galaxies and their contribution to the cosmic infrared background
• Far-infrared surveys of galaxy evolution
• Sub-millimetre observations of the Hubble Deep Field and Flanking Fields
• SCUBA-2 Ultra Deep Imaging EAO Survey (STUDIES): Faint-End Counts at 450 um
• Learning to Denoise Astronomical Images with U-nets
• HerMES: SPIRE Science Demonstration Phase Maps
• EGG: hatching a mock Universe from empirical prescriptions
• GOODS-ALMA: 1.1 mm galaxy survey - I. Source catalogue and optically dark galaxies
• The Dragonfly Wide Field Survey. I. Telescope, Survey Design and Data Characterization
• Candidate high-z proto-clusters among the Planck compact sources, as revealed by Herschel-SPIRE
• Ultra-Red Galaxies Signpost Candidate Proto-Clusters at High Redshift
• JINGLE, a JCMT legacy survey of dust and gas for galaxy evolution studies: II. SCUBA-2 850 μm data reduction and dust flux density catalogues
• Deep Learning for Line Intensity Mapping Observations: Information Extraction from Noisy Maps
• Data--driven Image Restoration with Option--driven Learning for Big and Small Astronomical Image Datasets
• Over-density of SMGs in fields containing z~0.3 galaxies: magnification bias and the implications for studies of galaxy evolution
• How far can we push deconvolution? A SCUBA-2 test case

Cited by in corpus (8)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• Deep Learning-Based Super-Resolution and De-Noising for XMM-Newton Images
• Detecting gravitational lenses using machine learning: exploring interpretability and sensitivity to rare lensing configurations
• Confusion of extragalactic sources in the far infrared: a baseline assessment of the performance of PRIMAger in intensity and polarization
• MaLeFiSenta: Machine Learning for FilamentS Identification and orientation in the ISM
• The Three Hundred Project: Mapping The Matter Distribution in Galaxy Clusters Via Deep Learning from Multiview Simulated Observations
• Reconstructing the mid-infrared spectra of galaxies using ultraviolet to submillimeter photometry and Deep Generative Networks