Issue |
A&A
Volume 656, December 2021
|
|
---|---|---|
Article Number | A62 | |
Number of page(s) | 18 | |
Section | Numerical methods and codes | |
DOI | https://doi.org/10.1051/0004-6361/202141193 | |
Published online | 03 December 2021 |
Identification of point sources in gamma rays using U-shaped convolutional neural networks and a data challenge⋆
1
Pontificia Universidad Católica de Chile, Avenida Vicuña Mackenna 4860, Macul, Región Metropolitana, Chile
e-mail: bpanes@astro.puc.cl, bapanes@gmail.com
2
Center for Astrophysics and Cosmology, University of Nova Gorica, Vipavska 13, 5000 Nova Gorica, Slovenia
3
Univ. Grenoble Alpes, USMB, CNRS, LAPTh, 74000 Annecy, France
4
High Energy Physics, Radboud University Nijmegen, Heyendaalseweg 135, 6525 AJ Nijmegen, The Netherlands
5
Nikhef, Science Park 105, 1098 XG Amsterdam, The Netherlands
6
NHL Stenden University of Applied Sciences, Professorship Computer Vision & Data Science, Leeuwarden, The Netherlands
7
Science Institute, University of Iceland, 107 Reykjavik, Iceland
8
Nordita, KTH Royal Institute of Technology and Stockholm University, Roslagstullsbacken 23, 106 91 Stockholm, Sweden
9
Instituto de Física Corpuscular, IFIC-UV/CSIC, Valencia, Spain
Received:
27
April
2021
Accepted:
20
August
2021
Context. At GeV energies, the sky is dominated by the interstellar emission from the Galaxy. With limited statistics and spatial resolution, accurately separating point sources is therefore challenging.
Aims. Here we present the first application of deep learning based algorithms to automatically detect and classify point sources from gamma-ray data. For concreteness we refer to this approach as AutoSourceID.
Methods. To detect point sources, we utilized U-shaped convolutional networks for image segmentation and k-means for source clustering and localization. We also explored the Centroid-Net algorithm, which is designed to find and count objects. Using two algorithms allows for a cross check of the results, while a combination of their results can be used to improve performance. The training data are based on 9.5 years of exposure from The Fermi Large Area Telescope (Fermi-LAT) and we used source properties of active galactic nuclei (AGNs) and pulsars (PSRs) from the fourth Fermi-LAT source catalog in addition to several models of background interstellar emission. The results of the localization algorithm are fed into a classification neural network that is trained to separate the three general source classes (AGNs, PSRs, and FAKE sources).
Results. We compared our localization algorithms qualitatively with traditional methods and find them to have similar detection thresholds. We also demonstrate the robustness of our source localization algorithms to modifications in the interstellar emission models, which presents a clear advantage over traditional methods. The classification network is able to discriminate between the three classes with typical accuracy of ∼70%, as long as balanced data sets are used in classification training. We published online our training data sets and analysis scripts and invite the community to join the data challenge aimed to improve the localization and classification of gamma-ray point sources.
Key words: catalogs / gamma rays: general / astroparticle physics / methods: numerical / methods: data analysis / techniques: image processing
© ESO 2021
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.