Reconstruction of stereoscopic CTA events using deep learning with CTLearn

Discussion timeslot (ZOOM-Meeting): 13. July 2021 - 12:00
ZOOM-Meeting URL: https://desy.zoom.us/j/98542982538
ZOOM-Meeting ID: 98542982538
ZOOM-Meeting Passcode: ICRC2021
Corresponding Session: https://icrc2021-venue.desy.de/channel/52-Analysis-Methods-Catalogues-Community-Tools-Machine-Learning-GAD-GAI/64
Live-Stream URL: https://icrc2021-venue.desy.de/livestream/Discussion-04/5

Abstract:
'The Cherenkov Telescope Array (CTA), conceived as an array of tens of imaging atmosphericrnCherenkov telescopes (IACTs), is an international project for a next-generation ground-basedrngamma-ray observatory, aiming to improve on the sensitivity of current-generation instrumentsrnby an order of magnitude and provide energy coverage from 20 GeV to more than 300 TeV.rnArrays of IACTs probe the very-high-energy gamma-ray sky. Their workingrnprinciple consists of the simultaneous observation of air showers initiated byrnthe interaction of very-high-energy gamma rays and cosmic rays with the atmosphere.rnCherenkov photons induced by a given shower are focused onto the camera planernof the telescopes in the array, producing a multi-stereoscopic record of the event. Thisrnimage contains the longitudinal development of the air shower, togetherrnwith its spatial, temporal, and calorimetric information. The properties ofrnthe originating very-high-energy particle (type, energy and incoming direction)rncan be inferred from those images by reconstructing the full event using machinernlearning techniques. In this contribution, we present a purely deep-learningrndriven, full-event reconstruction of simulated, stereoscopic IACT eventsrnusing CTLearn. CTLearn is a package that includes modules for loadingrnand manipulating IACT data and for running deep learning models,rnusing pixel-wise camera data as input.'

Authors: Tjark Miener
Co-Authors: Daniel Nieto Castaño | Aryeh Brill | Samuel Timothy Spencer | Jose Luis Contreras | for the CTA Collaboration

Collaboration: CTA

Indico-ID: 710
Proceeding URL: https://pos.sissa.it/395/730