Deep Learning application for stellar parameters determination: III- Denoising Procedure

TL;DR

This study evaluates the effectiveness of denoising techniques, including autoencoders and PCA, on synthetic stellar spectra for accurate parameter derivation, finding no significant accuracy improvement after denoising.

Contribution

It introduces and compares two denoising methods for stellar spectra and assesses their impact on stellar parameter estimation accuracy.

Findings

Denoising does not improve parameter accuracy for synthetic spectra.

Autoencoder and PCA methods perform similarly in denoising.

Denoising techniques do not enhance neural network parameter predictions.

Abstract

In this third paper in a series, we investigate the need of spectra denoising for the derivation of stellar parameters. We have used two distinct datasets for this work. The first one contains spectra in the range of 4450-5400 {\AA} at a resolution of 42000 and the second in the range of 8400-8800 {\AA} at a resolution of 11500. We constructed two denoising techniques, an autoencoder, and a Principal Component Analysis. Using random Gaussian noise added to synthetic spectra, we have trained a Neural Network to derive the stellar parameters Teff, log g, ve sin i, {\xi}t, and [M/H] of the denoised spectra. We find that, independently of the denoising technique, the stellar parameters accuracy values do not improve once we denoise the synthetic spectra. This is true with and without applying data augmentation to the stellar parameters Neural Network.