SUPPNet: Neural network for stellar spectrum normalisation

Abstract

Precise continuum normalisation of merged échelle spectra is a demanding task necessary for various detailed spectroscopic analyses. Automatic methods have limited effectiveness due to the variety of features present in the spectra of stars. This complexity often leads to the necessity of manual normalisation which is a time demanding task. The aim of this work is to develop a fully automated normalisation tool that works with order-merged spectra and offers flexible manual fine-tuning, if necessary. The core of the proposed method uses the novel fully convolutional deep neural network (SUPP Network) that was trained to predict a pseudo-continuum. The post-processing step uses smoothing splines that gives access to regressed knots useful for optional manual corrections. The active learning technique was applied to deal with possible biases that may arise from training with synthetic spectra and to extend the applicability of the proposed method to features absent in this kind of spectra. The developed normalisation method was tested with high-resolution spectra of stars having spectral types from O to G, and gave root mean squared (RMS) error over the set of test stars equal $0.0128$ in the spectral range from $3900\mathring{A}$ to $7000\mathring{A}$ and $0.0081$ in the range from $4200\mathring{A}$ to $7000\mathring{A}$. Experiments with synthetic spectra give RMS of the order of $0.0050$. The proposed method gives results comparable to careful manual normalisation. Additionally, this approach is general and can be used in other fields of astronomy where background modelling or trend removal is a part of data processing. The algorithm is available online at https://git.io/JqJhf.

20 pages (incl. appendix), 30 figures, 4 tables. Revised based on the reviewers' comments and submitted to A&A

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• The Gaia mission
• A Grid of NLTE Line-Blanketed Model Atmospheres of Early B-type Stars
• Machine Learning for the Zwicky Transient Facility
• Machine Learning in Astronomy: a practical overview
• High-precision abundances of elements in solar-type stars. Evidence of two distinct sequences in abundance-age relations
• RASSINE: Interactive tool for normalising stellar spectra I. Description and performance of the code
• Modeling the Echelle Spectra Continuum with Alpha Shapes and Local Regression Fitting

Cited by in corpus (10)

• MELCHIORS: The Mercator Library of High Resolution Stellar Spectroscopy
• Prospects for future studies using deep imaging: Analysis of individual Galactic cirrus filaments
• The problem of dust attenuation in photometric decomposition of edge-on galaxies and possible solutions
• Exploring extreme brightness variations in blue supergiant MACHO 80.7443.1718: Evidence for companion-driven enhanced mass loss
• Solar Flux Atlases: The new HARPS-N Quiet Sun Benchmark and Ca II H & K Lines Continuum Normalisation
• High-resolution spectroscopy of detached eclipsing binaries during total eclipses
• Detailed Abundance Determination of Metal-Poor Stars with X-Shooter I. Unusual Chemistry in Halo Stars
• Playing CHESS with stars. I. Search for similar stars in large spectroscopic data sets
• A comprehensive study of $\delta$ Scuti-type pulsators in eclipsing binaries: oscillating eclipsing Algols
• The symphony of pulsations and binarity among massive stars using HERMES spectroscopy and TESS photometry