A novel stellar spectrum denoising method based on deep Bayesian modeling

TL;DR

This paper introduces a deep Bayesian modeling approach for stellar spectrum denoising that effectively handles noise correlation, sky emission lines, cosmic rays, and missing data, outperforming standard auto-encoders.

Contribution

It presents a novel deep Bayesian model incorporating priors, a spectrum generator, and a flow-based noise model for improved stellar spectrum denoising.

Findings

Outperforms standard denoising auto-encoder in quality

Effectively handles missing flux values

Reduces impact of sky emission lines and cosmic rays

Abstract

Spectrum denoising is an important procedure for large-scale spectroscopical surveys. This work proposes a novel stellar spectrum denoising method based on deep Bayesian modeling. The construction of our model includes a prior distribution for each stellar subclass, a spectrum generator and a flow-based noise model. Our method takes into account the noise correlation structure, and it is not susceptible to strong sky emission lines and cosmic rays. Moreover, it is able to naturally handle spectra with missing flux values without ad-hoc imputation. The proposed method is evaluated on real stellar spectra from the Sloan Digital Sky Survey (SDSS) with a comprehensive list of common stellar subclasses and compared to the standard denoising auto-encoder. Our denoising method demonstrates superior performance to the standard denoising auto-encoder, in respect of denoising quality and missing flux imputation. It may be potentially helpful in improving the accuracy of the classification and physical parameter measurement of stars when applying our method during data preprocessing.