Skip to main content
SearchLoginLogin or Signup

Classifying Serendipitous X-ray Sources with Machine Learning

Presentation #107.43 in the session Stellar/Compact Objects - Poster Session.

Published onMay 03, 2024
Classifying Serendipitous X-ray Sources with Machine Learning

High-energy astrophysics is currently in an unprecedented era with observatories such as Chandra, XMM-Newton, and eROSITA discovering millions of serendipitous X-ray sources. The nature of most of these X-ray sources remains unknown. Often, the X-ray data alone is not enough to reliably classify these sources, particularly for the faint sources whose population dominates these catalogs, so additional multi-wavelength data must be used. We have developed a multi-wavelength machine-learning classification pipeline (MUWCLASS), which can quickly perform classifications of a large number of CXO and XMM-Newton sources, taking into account multi-wavelength (e.g., optical, NIR, IR) information. Here we will discuss the results of several recent studies carried out using this pipeline in various environments, including unidentified Fermi-LAT and TeV sources and open clusters. We will also discuss upgrades we are making to the pipeline to incorporate new datasets with larger positional uncertainties (e.g., eROSITA). Lastly, we will outline some ideas for using community driven efforts to keep high energy training datasets (and source catalogs) up to date as we move into an era of rapid discovery of new sources.

No comments here