Machine Learning in Stellar Astronomy: Progress up to 2024

TL;DR

This paper reviews how machine learning techniques, especially deep learning, are transforming the analysis and understanding of diverse stellar objects and their properties in astronomy up to 2024.

Contribution

It provides a comprehensive overview of recent ML applications in stellar astronomy, highlighting advancements in classification and property inference of various stellar objects.

Findings

ML improves classification accuracy of stellar objects

Deep learning models enhance inference of stellar parameters

ML applications span a wide range of stellar and interstellar objects

Abstract

Machine learning (ML) has become a key tool in astronomy, driving advancements in the analysis and interpretation of complex datasets from observations. This article reviews the application of ML techniques in the identification and classification of stellar objects, alongside the inference of their key astrophysical properties. We highlight the role of both supervised and unsupervised ML algorithms, particularly deep learning models, in classifying stars and enhancing our understanding of essential stellar parameters, such as mass, age, and chemical composition. We discuss ML applications in the study of various stellar objects, including binaries, supernovae, dwarfs, young stellar objects, variables, metal-poor, and chemically peculiar stars. Additionally, we examine the role of ML in investigating star-related interstellar medium objects, such as protoplanetary disks, planetary nebulae, cold neutral medium, feedback bubbles, and molecular clouds.