A method based on Generative Adversarial Networks for disentangling physical and chemical properties of stars in astronomical spectra

TL;DR

This paper introduces a novel adversarial autoencoder-based method to disentangle physical and chemical properties in stellar spectra, improving interpretability and analysis of astronomical data.

Contribution

It presents a new adversarial training scheme with multiple discriminators for disentangling stellar parameters, and provides a versatile framework for the community.

Findings

Effective disentangling of temperature and gravity from spectra

Successful application to synthetic APOGEE and Gaia data

Open-source framework GANDALF for replication and extension

Abstract

Data compression techniques focused on information preservation have become essential in the modern era of big data. In this work, an encoder-decoder architecture has been designed, where adversarial training, a modification of the traditional autoencoder, is used in the context of astrophysical spectral analysis. The goal of this proposal is to obtain an intermediate representation of the astronomical stellar spectra, in which the contribution to the flux of a star due to the most influential physical properties (its surface temperature and gravity) disappears and the variance reflects only the effect of the chemical composition over the spectrum. A scheme of deep learning is used with the aim of unraveling in the latent space the desired parameters of the rest of the information contained in the data. This work proposes a version of adversarial training that makes use of a discriminator per parameter to be disentangled, thus avoiding the exponential combination that occurs in the use of a single discriminator, as a result of the discretization of the values to be untangled. To test the effectiveness of the method, synthetic astronomical data are used from the APOGEE and Gaia surveys. In conjunction with the work presented, we also provide a disentangling framework (GANDALF) available to the community, which allows the replication, visualization, and extension of the method to domains of any nature.