Machine learning based stellar classification with highly sparse photometry data

Abstract

Identifying stars belonging to different classes is vital in order to build up statistical samples of different phases and pathways of stellar evolution. In the era of surveys covering billions of stars, an automated method of identifying these classes becomes necessary. Many classes of stars are identified based on their emitted spectra. In this paper, we use a combination of the multi-class multi-label Machine Learning (ML) method XGBoost and the PySSED spectral-energy-distribution fitting algorithm to classify stars into nine different classes, based on their photometric data. The classifier is trained on subsets of the SIMBAD database. Particular challenges are the very high sparsity (large fraction of missing values) of the underlying data as well as the high class imbalance. We discuss the different variables available, such as photometric measurements on the one hand, and indirect predictors such as Galactic position on the other hand. We show the difference in performance when excluding certain variables, and discuss in which contexts which of the variables should be used. Finally, we show that increasing the number of samples of a particular type of star significantly increases the performance of the model for that particular type, while having little to no impact on other types. The accuracy of the main classifier is ~0.7 with a macro F1 score of 0.61. While the current accuracy of the classifier is not high enough to be reliably used in stellar classification, this work is an initial proof of feasibility for using ML to classify stars based on photometry.

References in corpus (22)

• XGBoost: A Scalable Tree Boosting System
• A Unified Approach to Interpreting Model Predictions
• Gaia Data Release 3: Summary of the content and survey properties
• The SIMBAD astronomical database
• High-Mass Star and Massive Cluster Formation in the Milky Way
• The Formation and Early Evolution of Low-mass Stars and Brown Dwarfs
• A Classification Scheme for Young Stellar Objects Using the WIDE-FIELD INFRARED SURVEY EXPLORER AllWISE Catalog: Revealing Low-Density Star Formation in the Outer Galaxy
• A recurrent neural network for classification of unevenly sampled variable stars
• The SAGE-Spec Spitzer Legacy program: The life-cycle of dust and gas in the Large Magellanic Cloud. Point source classification I
• New Insights into the Evolution of Massive Stars and Their Effects on Our Understanding of Early Galaxies
• Identifying galaxies, quasars, and stars with machine learning: A new catalogue of classifications for 111 million SDSS sources without spectra
• Binary Stars in the New Millennium
• Photometric redshift-aided classification using ensemble learning
• Optimizing exoplanet atmosphere retrieval using unsupervised machine-learning classification
• A Complete Census of Luminous Stellar Variability on Day to Decade Timescales
• Classification of Planetary Nebulae through Deep Transfer Learning
• Photometric identification of compact galaxies, stars and quasars using multiple neural networks
• Semi-Supervised Classification and Clustering Analysis for Variable Stars
• Photometric light curves classification with machine learning
• JWST observations of the Ring Nebula (NGC 6720): I. Imaging of the rings, globules, and arcs
• Machine learning-based photometric classification of galaxies, quasars, emission-line galaxies, and stars
• PySSED: an automated method of collating and fitting stellar spectral energy distributions