Radio surveys are widely used to study active galactic nuclei. Radio
interferometric observations typically trade-off surface brightness sensitivity
for angular resolution. Hence, observations using a wide range of baseline
lengths are required to recover both bright small-scale structures and diffuse
extended emission. We investigate if generative adversarial networks (GANs) can
extract additional information from radio data and might ultimately recover
extended flux from a survey with a high angular resolution and vice versa. We
use a GAN for the image-to-image translation between two different data sets,
namely the Faint Images of the Radio Sky at Twenty-Centimeters (FIRST) and the
NRAO VLA Sky Survey (NVSS) radio surveys. The GAN is trained to generate the
corresponding image cutout from the other survey for a given input. The results
are analyzed with a variety of metrics, including structural similarity as well
as flux and size comparison of the extracted sources. RadioGAN is able to
recover extended flux density within a $20\%$ margin for almost half of the
sources and learns more complex relations between sources in the two surveys
than simply convolving them with a different synthesized beam. RadioGAN is also
able to achieve subbeam resolution by recognizing complicated underlying
structures from unresolved sources. RadioGAN generates over a third of the
sources within a $20\%$ deviation from both original size and flux for the
FIRST to NVSS translation, while for the NVSS to FIRST mapping it achieves
almost $30\%$ within this range.
Description
RadioGAN - Translations between different radio surveys with generative adversarial networks
%0 Generic
%1 glaser2019radiogan
%A Glaser, Nina
%A Wong, O Ivy
%A Schawinski, Kevin
%A Zhang, Ce
%D 2019
%K clean radioGAN
%R 10.1093/mnras/stz1534
%T RadioGAN - Translations between different radio surveys with generative
adversarial networks
%U http://arxiv.org/abs/1906.03874
%X Radio surveys are widely used to study active galactic nuclei. Radio
interferometric observations typically trade-off surface brightness sensitivity
for angular resolution. Hence, observations using a wide range of baseline
lengths are required to recover both bright small-scale structures and diffuse
extended emission. We investigate if generative adversarial networks (GANs) can
extract additional information from radio data and might ultimately recover
extended flux from a survey with a high angular resolution and vice versa. We
use a GAN for the image-to-image translation between two different data sets,
namely the Faint Images of the Radio Sky at Twenty-Centimeters (FIRST) and the
NRAO VLA Sky Survey (NVSS) radio surveys. The GAN is trained to generate the
corresponding image cutout from the other survey for a given input. The results
are analyzed with a variety of metrics, including structural similarity as well
as flux and size comparison of the extracted sources. RadioGAN is able to
recover extended flux density within a $20\%$ margin for almost half of the
sources and learns more complex relations between sources in the two surveys
than simply convolving them with a different synthesized beam. RadioGAN is also
able to achieve subbeam resolution by recognizing complicated underlying
structures from unresolved sources. RadioGAN generates over a third of the
sources within a $20\%$ deviation from both original size and flux for the
FIRST to NVSS translation, while for the NVSS to FIRST mapping it achieves
almost $30\%$ within this range.
@misc{glaser2019radiogan,
abstract = {Radio surveys are widely used to study active galactic nuclei. Radio
interferometric observations typically trade-off surface brightness sensitivity
for angular resolution. Hence, observations using a wide range of baseline
lengths are required to recover both bright small-scale structures and diffuse
extended emission. We investigate if generative adversarial networks (GANs) can
extract additional information from radio data and might ultimately recover
extended flux from a survey with a high angular resolution and vice versa. We
use a GAN for the image-to-image translation between two different data sets,
namely the Faint Images of the Radio Sky at Twenty-Centimeters (FIRST) and the
NRAO VLA Sky Survey (NVSS) radio surveys. The GAN is trained to generate the
corresponding image cutout from the other survey for a given input. The results
are analyzed with a variety of metrics, including structural similarity as well
as flux and size comparison of the extracted sources. RadioGAN is able to
recover extended flux density within a $20\%$ margin for almost half of the
sources and learns more complex relations between sources in the two surveys
than simply convolving them with a different synthesized beam. RadioGAN is also
able to achieve subbeam resolution by recognizing complicated underlying
structures from unresolved sources. RadioGAN generates over a third of the
sources within a $20\%$ deviation from both original size and flux for the
FIRST to NVSS translation, while for the NVSS to FIRST mapping it achieves
almost $30\%$ within this range.},
added-at = {2019-06-11T15:47:58.000+0200},
author = {Glaser, Nina and Wong, O Ivy and Schawinski, Kevin and Zhang, Ce},
biburl = {https://www.bibsonomy.org/bibtex/2acf110d0e3b36c579cb9930398293576/heh15},
description = {RadioGAN - Translations between different radio surveys with generative adversarial networks},
doi = {10.1093/mnras/stz1534},
interhash = {1441426e7c8d005d20a8cbfb6feb6b95},
intrahash = {acf110d0e3b36c579cb9930398293576},
keywords = {clean radioGAN},
note = {cite arxiv:1906.03874},
timestamp = {2019-06-11T15:47:58.000+0200},
title = {RadioGAN - Translations between different radio surveys with generative
adversarial networks},
url = {http://arxiv.org/abs/1906.03874},
year = 2019
}