Unsupervised Spectral Unmixing For Telluric Correction Using A Neural Network Autoencoder

TL;DR

This paper introduces a neural network autoencoder method for unsupervised spectral unmixing to correct telluric absorption in ground-based astronomical spectra, improving efficiency and accuracy over traditional synthetic models.

Contribution

The novel autoencoder approach automatically extracts telluric transmission spectra from observed data without supervision, enabling efficient correction of atmospheric absorption effects.

Findings

Accurately separates telluric components from observed spectra.

Reduces computational cost compared to synthetic models.

Effectively removes water and oxygen absorption features.

Abstract

The absorption of light by molecules in the atmosphere of Earth is a complication for ground-based observations of astrophysical objects. Comprehensive information on various molecular species is required to correct for this so called telluric absorption. We present a neural network autoencoder approach for extracting a telluric transmission spectrum from a large set of high-precision observed solar spectra from the HARPS-N radial velocity spectrograph. We accomplish this by reducing the data into a compressed representation, which allows us to unveil the underlying solar spectrum and simultaneously uncover the different modes of variation in the observed spectra relating to the absorption of $\mathrm{H_2O}$ and $\mathrm{O_2}$ in the atmosphere of Earth. We demonstrate how the extracted components can be used to remove $\mathrm{H_2O}$ and $\mathrm{O_2}$ tellurics in a validation observation with similar accuracy and at less computational expense than a synthetic approach with molecfit.