https://doi.org/10.1051/epjconf/202531906009
Classification of Fermi-LAT unassociated sources with machine learning in the presence of dataset shifts
Erlangen Centre for Astroparticle Physics, Nikolaus-Fiebiger-Str. 2, Erlangen 91058, Germany
* e-mail: dmitry.malyshev@fau.de
Published online: 6 March 2025
About one third of Fermi-LAT sources are unassociated. We perform multi-class classification of Fermi-LAT sources using machine learning with the goal of probabilistic classification of the unassociated sources. A particular attention is paid to the fact that the distributions of associated and unassociated sources are different as functions of source parameters. In this work, we address this problem in the framework of dataset shifts in machine learning.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
