We present a neural network autoencoder structure that is able to extract the most important latent spectral features from observed spectra and reconstruct a spectrum from those features. Because of the training process, the network is able to reproduce a spectrum of high signal to noise ratio that does not show any spectral peculiarities. Such generated spectra were used to identify various emission features among spectra acquired by multiple surveys using the HERMES spectrograph. Emission features were identified by a direct comparison of the observed and generated spectrum. Using the described comparison procedure, we discovered 10.364 candidate stars with a prominent Halpha/Hbeta emission component produced by different physical mechanisms. Among them, we can find contributions of a nearby rarefied gas (identified trough emission of [NII] and [SII] lines) that was identified in 4004 spectra, which were not all identified as having Halpha emission.

The project has been discussed with Maruša and Mark an does not overlap with their work.

Please send comments and authorship requests to klemen [dot] cotarfmf [dot] uni-lj [dot] si

Paper PDF: 

galah_emission-line_stars.pdf