Learning novel representations of variable sources from multi-modal $\text{Gaia}$ data via autoencoders

Abstract

Gaia Data Release 3 (DR3) published for the first time epoch photometry, BP/RP (XP) low-resolution mean spectra, and supervised classification results for millions of variable sources. This extensive dataset offers a unique opportunity to study their variability by combining multiple Gaia data products. In preparation for DR4, we propose and evaluate a machine learning methodology capable of ingesting multiple Gaia data products to achieve an unsupervised classification of stellar and quasar variability. A dataset of 4 million Gaia DR3 sources is used to train three variational autoencoders (VAE), which are artificial neural networks (ANNs) designed for data compression and generation. One VAE is trained on Gaia XP low-resolution spectra, another on a novel approach based on the distribution of magnitude differences in the Gaia G band, and the third on folded Gaia G band light curves. Each Gaia source is compressed into 15 numbers, representing the coordinates in a 15-dimensional latent space generated by combining the outputs of these three models. The learned latent representation produced by the ANN effectively distinguishes between the main variability classes present in Gaia DR3, as demonstrated through both supervised and unsupervised classification analysis of the latent space. The results highlight a strong synergy between light curves and low-resolution spectral data, emphasising the benefits of combining the different Gaia data products. A two-dimensional projection of the latent variables reveals numerous overdensities, most of which strongly correlate with astrophysical properties, showing the potential of this latent space for astrophysical discovery. We show that the properties of our novel latent representation make it highly valuable for variability analysis tasks, including classification, clustering and outlier detection.

Manuscript accepted on Astronomy & Astrophysics, 20 pages, 20 figures, 2 tables

References in corpus (35)

• XGBoost: A Scalable Tree Boosting System
• The Gaia mission
• Gaia Data Release 3: Summary of the content and survey properties
• Deep Learning for Anomaly Detection: A Review
• The Zwicky Transient Facility: System Overview, Performance, and First Results
• astroquery: An Astronomical Web-Querying Package in Python
• A First Catalog of Variable Stars Measured by the Asteroid Terrestrial-impact Last Alert System (ATLAS)
• The Early Data Release of the Dark Energy Spectroscopic Instrument
• Probing the interior physics of stars through asteroseismology
• Horizontal Branch Stars: The Interplay between Observations and Theory, and Insights into the Formation of the Galaxy
• The SED Machine: a robotic spectrograph for fast transient classification
• Gaia Data Release 3: Processing and validation of BP/RP low-resolution spectral data
• Gaia Data Release 3. Summary of the variability processing and analysis
• A recurrent neural network for classification of unevenly sampled variable stars
• Internal calibration of Gaia BP/RP low-resolution spectra
• Gaia Data Release 3. The first Gaia catalogue of eclipsing binary candidates
• Gaia Data Release 3: All-sky classification of 12.4 million variable sources into 25 classes
• Gaia Data Release 3: The second Gaia catalogue of Long-Period Variable candidates
• Variable stars across the observational HR diagram
• AstroCLIP: A Cross-Modal Foundation Model for Galaxies
• Gaia Data Release 3: Pulsations in main sequence OBAF-type stars
• Gaia Data Release 3: Cross-match of Gaia sources with variable objects from the literature
• Gaia Data Release 3: Gaia scan-angle dependent signals and spurious periods
• Deep-Learnt Classification of Light Curves
• Searching for changing-state AGNs in massive datasets -- I: applying deep learning and anomaly detection techniques to find AGNs with anomalous variability behaviours
• On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars
• ASTROMER: A transformer-based embedding for the representation of light curves
• Gaia Data Release 3: G_RVS photometry from the RVS spectra
• On the co-existence of chemically peculiar Bp stars, slowly pulsating B stars and constant B stars in the same part of the H-R diagram
• Confronting sparse Gaia DR3 photometry with TESS for a sample of around 60,000 OBAF-type pulsators
• Gaia Data Release 3: The Gaia Andromeda Photometric Survey
• Gaia Data Release 3: The first Gaia catalogue of variable AGN
• Blazhko effect in the Galactic bulge fundamental mode RR Lyrae stars II: Modulation shapes, amplitudes and periods
• A classification algorithm for time-domain novelties in preparation for LSST alerts: Application to variable stars and transients detected with DECam in the Galactic Bulge
• Mode identification and ensemble asteroseismology of 119 $\beta$ Cep stars detected by Gaia light curves and monitored by TESS

Cited by in corpus (3)

• Deep learning-based astronomical multimodal data fusion: A comprehensive review
• Automated all-sky detection of γ Doradus / δ Scuti hybrids in TESS data from positive unlabelled (PU) learning
• Exploring Late Stellar Evolution in the Era of Large Surveys: Machine Learning Prospects for Hot Subdwarfs and White Dwarfs