The GALAH survey: Characterization of emission-line stars with spectral modelling using autoencoders. (arXiv:2006.03062v1 [astro-ph.SR])
<a href="http://arxiv.org/find/astro-ph/1/au:+Cotar_K/0/1/0/all/0/1">Klemen Čotar</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Zwitter_T/0/1/0/all/0/1">Tomaž Zwitter</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Traven_G/0/1/0/all/0/1">Gregor Traven</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Bland_Hawthorn_J/0/1/0/all/0/1">Joss Bland-Hawthorn</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Buder_S/0/1/0/all/0/1">Sven Buder</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Hayden_M/0/1/0/all/0/1">Michael R. Hayden</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Kos_J/0/1/0/all/0/1">Janez Kos</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Lewis_G/0/1/0/all/0/1">Geraint F. Lewis</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Martell_S/0/1/0/all/0/1">Sarah L. Martell</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Nordlander_T/0/1/0/all/0/1">Thomas Nordlander</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Stello_D/0/1/0/all/0/1">Dennis Stello</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Horner_J/0/1/0/all/0/1">Jonathan Horner</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Ting_Y/0/1/0/all/0/1">Yuan-Sen Ting</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Zerjal_M/0/1/0/all/0/1">Maruša Žerjal</a>
We present a neural network autoencoder structure that is able to extract
essential latent spectral features from observed spectra and then reconstruct a
spectrum from those features. Because of the training with a set of unpeculiar
spectra, the network is able to reproduce a spectrum of high signal-to-noise
ratio that does not show any spectral peculiarities even if they are present in
an observed spectrum. Spectra generated in this manner were used to identify
various emission features among spectra acquired by multiple surveys using the
HERMES spectrograph at the Anglo-Australian telescope. Emission features were
identified by a direct comparison of the observed and generated spectra. Using
the described comparison procedure, we discovered 10,364 candidate spectra with
a varying degree of H$alpha$/H$beta$ emission component produced by different
physical mechanisms. A fraction of those spectra belongs to the repeated
observation that shows temporal variability in their emission profile. Among
emission spectra, we find objects that feature contributions of a nearby
rarefied gas (identified through the emission of [NII] and [SII] lines) that
was identified in 4004 spectra, which were not all identified as having
H$alpha$ emission. Positions of identified emission-line objects coincide with
multiple known regions that harbour young stars. Similarly, detected nebular
emission spectra coincide with visually-prominent nebular clouds observable in
the red all-sky photographic composites.
We present a neural network autoencoder structure that is able to extract
essential latent spectral features from observed spectra and then reconstruct a
spectrum from those features. Because of the training with a set of unpeculiar
spectra, the network is able to reproduce a spectrum of high signal-to-noise
ratio that does not show any spectral peculiarities even if they are present in
an observed spectrum. Spectra generated in this manner were used to identify
various emission features among spectra acquired by multiple surveys using the
HERMES spectrograph at the Anglo-Australian telescope. Emission features were
identified by a direct comparison of the observed and generated spectra. Using
the described comparison procedure, we discovered 10,364 candidate spectra with
a varying degree of H$alpha$/H$beta$ emission component produced by different
physical mechanisms. A fraction of those spectra belongs to the repeated
observation that shows temporal variability in their emission profile. Among
emission spectra, we find objects that feature contributions of a nearby
rarefied gas (identified through the emission of [NII] and [SII] lines) that
was identified in 4004 spectra, which were not all identified as having
H$alpha$ emission. Positions of identified emission-line objects coincide with
multiple known regions that harbour young stars. Similarly, detected nebular
emission spectra coincide with visually-prominent nebular clouds observable in
the red all-sky photographic composites.
http://arxiv.org/icons/sfx.gif
