Super-resolving Herschel : A deep-learning-based deconvolution and denoising technique

Astronomy and Astrophysics, vol. 713, pp. A23

Abstract

Aims. Dusty star-forming galaxies (DSFGs) dominate the far-infrared (FIR) and sub-millimetre (sub-mm) number counts, but singledish surveys at these wavelengths suffer from poor angular resolution, making identifications of multi-wavelength counterparts difficult. Prior driven deblending techniques require extensive fine-tuning and struggle to process large fields. This work aims to develop a fast and reliable deep-learning-based deconvolution and denoising super-resolution (SR) technique. Methods. We employed a transformer neural network to improve the resolution of the Herschel /SPIRE 500 µm observations by a factor of 4.5, with input comprised of Spitzer /MIPS 24µm and Herschel /SPIRE 250, 350, 500 µm images. The network was trained on simulations from SIDES and SHARK. To mimic realistic observations, we injected instrumental noise into the input simulated images, while keeping the target images noise-free to enhance the de-noising capabilities of our method. We evaluated the performance of our method on simulated test sets and real JCMT/SCUBA-2 450 µm observations in the COSMOS field that have a superior resolution compared to Herschel . Results. Our SR method achieves an inference time of ∼1 s/deg 2 on consumer-grade GPUs, which is much faster than traditional deblending techniques. Using the simulation test sets, we show that fluxes of the extracted sources from the super-resolved image are accurate to within 5% for sources with an intrinsic flux ≳8 mJy, which is a substantial improvement compared to blind extraction on the native images. Astrometric error is low, at ≲1″ compared to the 12″ pixel scale. In terms of reliability and completeness, ≳90% of the extracted sources brighter than ∼3 mJy are reliable and more than 90% of the input sources with intrinsic fluxes ≳5 mJy are recovered. When applied to the real 500 µm observations, the fluxes of the extracted sources from the super-resolved map agree well with the SCUBA-2 measured fluxes (after converting the 450 µm fluxes to 500 µm using a correction factor of 0.84) for sources above ∼10 mJy. Our 500 µm number counts are also consistent with previous SCUBA-2 measurements. Thanks to its speed, our technique enables SR over hundreds of deg 2 without the need for fine-tuning, facilitating statistical analysis of DSFGs.

Authors 12

1. Dennis Koopmans Aachen SRON Netherlands Institute for Space Research

   University of Groningen · Space Research Organisation Netherlands

   Affiliation as printed

   Kapteyn Astronomical Institute, University of Groningen

   SRON Netherlands Institute for Space Research

2. Lingyu Wang Aachen SRON Netherlands Institute for Space Research

   University of Groningen · Space Research Organisation Netherlands

   Affiliation as printed

   Kapteyn Astronomical Institute, University of Groningen

   SRON Netherlands Institute for Space Research

3. Berta Margalef-Bentabol Aachen SRON Netherlands Institute for Space Research

   Space Research Organisation Netherlands

   Affiliation as printed

   SRON Netherlands Institute for Space Research

4. Antonio La Marca Aachen SRON Netherlands Institute for Space Research

   University of Groningen · European Space Agency · European Space Research and Technology Centre · Space Research Organisation Netherlands

   Affiliation as printed

   European Space Agency/ESTEC

   Kapteyn Astronomical Institute, University of Groningen

   SRON Netherlands Institute for Space Research

5. M. Béthermin

   Centre National de la Recherche Scientifique · Observatoire astronomique de Strasbourg · Université de Strasbourg

   Affiliation as printed

   Université de Strasbourg, CNRS, Observatoire astronomique de Strasbourg

6. Laura Bisigello

   Osservatorio Astronomico di Padova · National Institute for Astrophysics

   Affiliation as printed

   INAF-Osservatorio Astronomico di Padova

7. Zhen-Kai Gao

   Institute of Astronomy and Astrophysics, Academia Sinica · National Central University · Academia Sinica

   Affiliation as printed

   Academia Sinica Institute of Astronomy and Astrophysics (ASIAA)

   Graduate Institute of Astronomy, National Central University

8. Claudia del P. Lagos

   The University of Western Australia · ASTRO-3D · ARC Centre of Excellence for All-sky Astrophysics · International Centre for Radio Astronomy Research

   Affiliation as printed

   ARC Centre of Excellence for All Sky Astrophysics in 3 Dimensions (ASTRO 3D)

   Cosmic Dawn Center (DAWN)

   International Centre for Radio Astronomy Research (ICRAR), M468, University of Western Australia

9. Lynge Lauritsen

   The Open University

   Affiliation as printed

   School of Physical Sciences, Faculty of Science, Technology, Engineering & Mathematics, The Open University

10. Stephen Serjeant

    The Open University

    Affiliation as printed

    School of Physical Sciences, Faculty of Science, Technology, Engineering & Mathematics, The Open University

11. Floris F. S. van der Tak Aachen SRON Netherlands Institute for Space Research

    University of Groningen · Space Research Organisation Netherlands

    Affiliation as printed

    Kapteyn Astronomical Institute, University of Groningen

    SRON Netherlands Institute for Space Research

12. Wei-Hao Wang

    Institute of Astronomy and Astrophysics, Academia Sinica · Academia Sinica

    Affiliation as printed

    Academia Sinica Institute of Astronomy and Astrophysics (ASIAA)