Investigating the VHE Gamma-ray Sources Using Deep Neural Networks
Vodeb V, Bhattacharyya S, Principe G, Zaharijaš G, Austri R, Stoppa F, Caron S, Malyshev D (2024)
Publication Type: Conference contribution
Publication year: 2024
Journal
Publisher: Sissa Medialab Srl
Book Volume: 444
Conference Proceedings Title: Proceedings of Science
Event location: Nagoya, JPN
Abstract
The upcoming Cherenkov Telescope Array (CTA) will dramatically improve the point-source sensitivity compared to the current Imaging Atmospheric Cherenkov Telescopes (IACTs). One of the key science projects of CTA will be a survey of the whole Galactic plane (GPS) using both southern and northern observatories, specifically focusing on the inner galactic region. We extend a deep learning-based image segmentation software pipeline (autosource-id) developed on Fermi-LAT data to detect and classify extended sources for the simulated CTA GPS. Using updated instrument response functions for CTA (Prod5), we test this pipeline on simulated gamma-ray sources lying in the inner galactic region (specifically 0◦ < l < 20◦, |b| < 3◦) for energies ranging from 30 GeV to 100 TeV. Dividing the source extensions ranging from 0.03◦ to 1◦ in three different classes, we find that using a simple and light convolutional neural network it is possible to achieve a 97% global accuracy in separating the extended sources from the point-like sources. The neural net architecture including other data pre-processing codes is available online.
Authors with CRIS profile
Involved external institutions
University of Nova Gorica / Univerza v Novi Gorici
Slovenia (SI)
Institute for Corpuscular Physics / Instituto de Física Corpuscular (IFIC)
Spain (ES)
Radboud University Nijmegen
Netherlands (NL)
National Institute for Nuclear Physics / Istituto Nazionale di Fisica Nucleare (INFN)
Italy (IT)
Slovenia (SI)
Institute for Corpuscular Physics / Instituto de Física Corpuscular (IFIC)
Spain (ES)
Radboud University Nijmegen
Netherlands (NL)
National Institute for Nuclear Physics / Istituto Nazionale di Fisica Nucleare (INFN)
Italy (IT)
How to cite
APA:
Vodeb, V., Bhattacharyya, S., Principe, G., Zaharijaš, G., Austri, R., Stoppa, F.,... Malyshev, D. (2024). Investigating the VHE Gamma-ray Sources Using Deep Neural Networks. In Proceedings of Science. Nagoya, JPN: Sissa Medialab Srl.
MLA:
Vodeb, V., et al. "Investigating the VHE Gamma-ray Sources Using Deep Neural Networks." Proceedings of the 38th International Cosmic Ray Conference, ICRC 2023, Nagoya, JPN Sissa Medialab Srl, 2024.
BibTeX: Download