Papers
arxiv:2504.11529

A Machine Learning Framework for Stellar Collision Transient Identification

Published on Apr 15
Authors:
,

Abstract

Modern astronomical surveys, such as the Zwicky Transient Facility (ZTF), are capable of detecting thousands of transient events per year, necessitating the use of automated and scalable data analysis techniques. Recent advances in machine learning have enabled the efficient classification and characterization of these transient phenomena. We aim to develop a fully systematic pipeline to identify candidate stellar collision events in galactic nuclei, which may otherwise be identified as tidal disruption events or other transients. We also seek to validate our simulations by comparing key physical parameters derived from observations and used in modeling these events. We generate a comprehensive bank of simulated light curves spanning a range of physical parameters and employ an approximate nearest neighbor algorithm (via the annoy library) to match these with observed ZTF light curves. Our pipeline is successfully able to associate observed ZTF light curves with simulated events. The resulting estimated parameters, including supermassive black hole masses and ejecta mass, are presented and compared to known values when applicable. We demonstrate that a systematic, machine learning-based approach can effectively identify and characterize stellar collision candidate events from large-scale transient surveys. This methodology is especially promising for future surveys which will provide us with significantly high volumes of data, such as LSST, where automated, data-intensive analysis will be critical for advancing our understanding of transient astrophysical phenomena.

Community

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2504.11529 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2504.11529 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2504.11529 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.