Disentangling stellar atmospheric parameters in astronomical spectra using Generative Adversarial Neural Networks

TL;DR

This paper introduces GANDALF, a GAN-based method that disentangles stellar atmospheric parameters from spectra by transforming data into a latent space, enabling more accurate and efficient property retrieval compared to traditional neural network approaches.

Contribution

The paper presents a novel GAN-based autoencoder framework for disentangling astrophysical parameters in stellar spectra, improving accuracy and reducing data dimensionality.

Findings

Achieved high accuracy in retrieving stellar parameters from Gaia DR3 spectra.

Demonstrated effective disentangling of physical and chemical properties.

Provided an open-source tool for community use.

Abstract

A method based on Generative Adversaria! Networks (GANs) is developed for disentangling the physical (effective temperature and gravity) and chemical (metallicity, overabundance of a-elements with respect to iron) atmospheric properties in astronomical spectra. Using a projection of the stellar spectra, commonly called latent space, in which the contribution dueto one or several main stellar physicochemical properties is minimised while others are enhanced, it was possible to maximise the information related to certain properties, which can then be extracted using artificial neural networks (ANN) as regressors with higher accuracy than a reference method based on the use of ANN trained with the original spectra. Methods. Our model utilises autoencoders, comprising two artificial neural networks: an encoder anda decoder which transform input data into a low-dimensional representation known as latent space. It also uses discriminators, which are additional neural networks aimed at transforming the traditional autoencoder training into an adversaria! approach, to disentangle or reinforce the astrophysical parameters from the latent space. The GANDALF tool is described. It was developed to define, train, and test our GAN model with a web framework to show how the disentangling algorithm works visually. It is open to the community in Github. Results. The performance of our approach for retrieving atmospheric stellar properties from spectra is demonstrated using Gaia Radial Velocity Spectrograph (RVS) data from DR3. We use a data-driven perspective and obtain very competitive values, ali within the literature errors, and with the advantage of an important dimensionality reduction of the data to be processed.