Comparative Study of Unsupervised Machine Learning Methods for Membership Association in Clusters Using GAIA DR3 Data
1 Jan 2023·
,,,·
0 min read
Anish Kalsi
D. tyagi
H. choudhary
A. kumar
Abstract
We perform a comparative study of unsupervised machine learning algorithms — including Gaussian Mixture
Models (GMM), DBSCAN, and pyUPMASK — for determining stellar membership probabilities in open clusters
using astrometric and photometric data from the Gaia DR3 catalogue. Our analysis demonstrates the
relative strengths and limitations of each method for cluster membership association.
Type
Publication
ICCASA 2023 Proceedings, European Chemical Bulletin
Authors
Anish Kalsi
(he/him)
Astronomy PhD Student
I am an Astrophysics PhD Candidate at the Nicolaus Copernicus Astronomical Center (NCAC PAS) in Poland,
currently bridging the gap between theoretical models and observational data.
With a background in Engineering Physics from Delhi Technological University and an MS in Astrophysics & Cosmology from the University of Padova,
Authors
Authors
Authors