Classification of evolved stars with (unsupervised) machine learning

Jiacheng Tan; Mel Krokos; Jamie  Welsh; Cristobal  Bordiu; Eva  Sciacca; Filomena  Bufano

doi:10.1007/978-3-031-34167-0_12

Classification of evolved stars with (unsupervised) machine learning

Jiacheng Tan, Mel Krokos, Jamie Welsh, Cristobal Bordiu, Eva Sciacca, Filomena Bufano

School of Computing

Istrituto Nazionale di Astrofisica, Catania, Italy

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper documents our analysis on the effectiveness of unsupervised machine learning algorithms for classification of evolved stars based on multi-wavelength photometric measurements. The foundation is a custom made reference dataset compiled from available stellar catalogues for target sources—AGB, Wolf Rayet, luminous blue variable and red supergiant stars. Our results indicate that applying HDBSCAN to UMAP’s feature representation seems to be the most effective approach for this usecase.

Original language	English
Title of host publication	Machine Learning for Astrophysics
Subtitle of host publication	Proceedings of the ML4Astro International Conference 30 May - 1 Jun 2022
Editors	Simone Riggi, Eva Sciacca, Francesco Schilliro
Publisher	Springer
Pages	57-60
Number of pages	4
ISBN (Electronic)	9783031341670
ISBN (Print)	9783031341663
DOIs	https://doi.org/10.1007/978-3-031-34167-0_12
Publication status	Published - 15 Oct 2023

Publication series

Name	Astrophysics and Space Science Proceedings
Publisher	Springer Nature
Volume	60
ISSN (Print)	1570-6591
ISSN (Electronic)	1570-6605

Keywords

Machine Learning
Astrophyics

Access to Document

10.1007/978-3-031-34167-0_12

Embargoed Document

ML4Astro___Proceedings___Jamie_Welsh
Accepted author manuscript (Post-print), 839 KB
Due to publisher’s copyright restrictions, this document is not freely available to download from this website until: 15/10/24

Cite this

Tan, J., Krokos, M., Welsh, J., Bordiu, C., Sciacca, E., & Bufano, F. (2023). Classification of evolved stars with (unsupervised) machine learning. In S. Riggi, E. Sciacca, & F. Schilliro (Eds.), Machine Learning for Astrophysics: Proceedings of the ML4Astro International Conference 30 May - 1 Jun 2022 (pp. 57-60). (Astrophysics and Space Science Proceedings; Vol. 60). Springer. https://doi.org/10.1007/978-3-031-34167-0_12

@inproceedings{964cf3ba54434fd79e5aac28141e9cb8,

title = "Classification of evolved stars with (unsupervised) machine learning",

abstract = "This paper documents our analysis on the effectiveness of unsupervised machine learning algorithms for classification of evolved stars based on multi-wavelength photometric measurements. The foundation is a custom made reference dataset compiled from available stellar catalogues for target sources—AGB, Wolf Rayet, luminous blue variable and red supergiant stars. Our results indicate that applying HDBSCAN to UMAP{\textquoteright}s feature representation seems to be the most effective approach for this usecase.",

keywords = "Machine Learning, Astrophyics",

author = "Jiacheng Tan and Mel Krokos and Jamie Welsh and Cristobal Bordiu and Eva Sciacca and Filomena Bufano",

year = "2023",

month = oct,

day = "15",

doi = "10.1007/978-3-031-34167-0_12",

language = "English",

isbn = "9783031341663",

series = "Astrophysics and Space Science Proceedings",

publisher = "Springer",

pages = "57--60",

editor = "Simone Riggi and Eva Sciacca and Francesco Schilliro",

booktitle = "Machine Learning for Astrophysics",

}

Tan, J , Krokos, M, Welsh, J, Bordiu, C, Sciacca, E & Bufano, F 2023, Classification of evolved stars with (unsupervised) machine learning. in S Riggi, E Sciacca & F Schilliro (eds), Machine Learning for Astrophysics: Proceedings of the ML4Astro International Conference 30 May - 1 Jun 2022. Astrophysics and Space Science Proceedings, vol. 60, Springer, pp. 57-60. https://doi.org/10.1007/978-3-031-34167-0_12

Classification of evolved stars with (unsupervised) machine learning. / Tan, Jiacheng ; Krokos, Mel; Welsh, Jamie et al.
Machine Learning for Astrophysics: Proceedings of the ML4Astro International Conference 30 May - 1 Jun 2022. ed. / Simone Riggi; Eva Sciacca; Francesco Schilliro. Springer, 2023. p. 57-60 (Astrophysics and Space Science Proceedings; Vol. 60).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Classification of evolved stars with (unsupervised) machine learning

AU - Tan, Jiacheng

AU - Krokos, Mel

AU - Welsh, Jamie

AU - Bordiu, Cristobal

AU - Sciacca, Eva

AU - Bufano, Filomena

PY - 2023/10/15

Y1 - 2023/10/15

N2 - This paper documents our analysis on the effectiveness of unsupervised machine learning algorithms for classification of evolved stars based on multi-wavelength photometric measurements. The foundation is a custom made reference dataset compiled from available stellar catalogues for target sources—AGB, Wolf Rayet, luminous blue variable and red supergiant stars. Our results indicate that applying HDBSCAN to UMAP’s feature representation seems to be the most effective approach for this usecase.

AB - This paper documents our analysis on the effectiveness of unsupervised machine learning algorithms for classification of evolved stars based on multi-wavelength photometric measurements. The foundation is a custom made reference dataset compiled from available stellar catalogues for target sources—AGB, Wolf Rayet, luminous blue variable and red supergiant stars. Our results indicate that applying HDBSCAN to UMAP’s feature representation seems to be the most effective approach for this usecase.

KW - Machine Learning

KW - Astrophyics

UR - https://www.consorzio-cometa.it/?p=659

U2 - 10.1007/978-3-031-34167-0_12

DO - 10.1007/978-3-031-34167-0_12

M3 - Conference contribution

SN - 9783031341663

T3 - Astrophysics and Space Science Proceedings

SP - 57

EP - 60

BT - Machine Learning for Astrophysics

A2 - Riggi, Simone

A2 - Sciacca, Eva

A2 - Schilliro, Francesco

PB - Springer

ER -

Tan J , Krokos M, Welsh J, Bordiu C, Sciacca E, Bufano F. Classification of evolved stars with (unsupervised) machine learning. In Riggi S, Sciacca E, Schilliro F, editors, Machine Learning for Astrophysics: Proceedings of the ML4Astro International Conference 30 May - 1 Jun 2022. Springer. 2023. p. 57-60. (Astrophysics and Space Science Proceedings). doi: 10.1007/978-3-031-34167-0_12