Potential of Gaia XP Spectra in Red Giant Star Asteroseismology: A Deep-Learning Approach

TL;DR

This study demonstrates that Gaia XP spectra, despite their low spectral resolution, contain sufficient information to accurately infer key asteroseismic parameters of red giant stars using deep learning models, enabling large-scale stellar population analysis.

Contribution

The paper introduces hybrid CNN-LSTM models trained on seismic data to extract asteroseismic parameters from Gaia XP spectra, extending seismic inference to millions of stars.

Findings

Models recover seismic parameters with accuracy comparable to moderate-resolution surveys.

Seismic predictions for over 2.5 million red giants enable large-scale population studies.

Saliency analysis identifies spectral regions linked to seismic sensitivity and stellar evolutionary states.

Abstract

Red giants are tracers of stellar evolution & Galactic structure & their asteroseismic properties, particularly large frequency separation, frequency of maximum oscillation power & dipole-mode period spacing, provide direct insight into their internal structure, masses & evolutionary states. Until now, seismic inferences on large stellar samples relied primarily on high-quality light curves from missions such as Kepler & TESS, or on moderate-resolution spectroscopy (LAMOST: R ~ 1800 & APOGEE: R ~ 22500) that clearly preserve information correlated with these seismic quantities. With Gaia XP spectra (R ~ 15-85), the possibility arises to extend asteroseismic measurements to orders of magnitude more stars, despite the much lower spectral res. . Our goal is to assess whether XP spectra retain enough information to enable reliable seismic inference for RGs. We develop hybrid CNN-LSTM models trained on RGs with seismic parameters measured from Kepler photometry. The networks learn the subtle spectral signatures, imprinted through global stellar properties, that correlate with \Delta\nu, \nu_max & \Delta\Pi_1. The models recover all three global asteroseismic parameters from Gaia XP spectra with accuracies comparable to results based on moderate-res. surveys such as LAMOST, demonstrating that even low-res. spectrophotometry carries sufficient information for seismic prediction. Saliency analysis reveals wavelength regions most strongly associated with seismic sensitivity & highlights physically distinct spectral behaviour between RGB & RC stars. Applying our models to Gaia DR3 yields seismic predictions for more than 2.5 M bright RGs, enabling population-level asteroseismic studies on an unprecedented scale. We also identify a small subset of low-\Delta\nu red clump candidates showing unusual spectral-seismic correlations, offering new avenues for investigating evolved stellar populations.