Deep-learning-driven event reconstruction applied to simulated data from a single Large-Sized Telescope of CTA

Grespan, Pietro; Nieto-Castaño, Daniel; Abe, Hyuga; Aguasca, Arnau; Agudo, I.; Antonelli, L. A.; Aramo, C.; Armstrong, T. P.; Artero, Manuel; Asano, Katsuaki; Ashkar, Halim; Aubert, Pierre; Baktash, Ali; Bamba, Aya; Larriva, Andres Baquero; Baroncelli, Leonardo; Almeida, U. Barres de; Barrio, J. A.; Batković, Ivana; González, J. Becerra; Bernardos, Mabel; Berti, Alessio; Biederbeck, Noah; Bigongiari, C.; Blanch, O.; Bonnoli, Giacomo; Bordas, P.; Bose, D.; Bulgarelli, A.; Burelli, Irene; Buscemi, Mario; Cardillo, M.; Caroff, S.; Carosi, A.; Cassol, Franca; Cerruti, M.; Chai, Yating; Cheng, K. S.; Chikawa, M.; Chytka, L.; Contreras, J. L.; Cortina, J.; Costantini, H.; Dalchenko, M.; Angelis, A. De; Lavergne, Mathieu de Bony de; Deleglise, Guillaume; Delgado, C.; Mengual, Jordi Delgado; Volpe, D. della; Depaoli, Davide; Pierro, F. Di; Venere, L. Di; Díaz, C.; Dominik, Rune Michael; Prester, D. Dominis; Donini, Alice; Dorner, D.; Doro, M.; Elsässer, Dominik; Emery, Gabriel; Escudero, Juan Pablo; Fiaßon, A.; Foffano, Luca; Fonseca, M. V.; Coromina, Lluis Freixas; Fukami, Satoshi; Fukazawa, Yasushi; García, Enrique; López, Ramon Garcia; Giglietto, N.; Giordano, F.; Gliwny, Paweł; Godinović, N.; Green, David; Gunji, Shuichi; Hackfeld, Jonas; Hadasch, D.; Hahn, Alexander; Hassan, Tarek; Hayashi, Kohei; Heckmann, Lea; Heller, M.; Llorente, Javier Herrera; Hirotani, Kouichi; Hoffmann, D.; Horns, D.; Houles, Julien; Hrabovský, M.; Hrupec, Dario; Hui, D. C. Y.; Hütten, Moritz; Inada, Tomohiro; Inome, Yusuke; Iori, M.; Ishio, Kazuma; Iwamura, Y.; Jacquemont, Mikaël; Martínez, Irene Jiménez; Jouvin, L.; Jurýšek, Jakub; Kagaya, Mika; Karas, Vladimír; Katagiri, H.; Kataoka, J.; Kerszberg, Daniel; Kobayashi, Yukiho; Kong, A. K. H.; Kubo, H.; Kushida, J.; Lamanna, G.; Lamastra, Alessandra; Flour, T. Le; Longo, F.; López-Coto, R.; López-Moya, Marcos; López-Oramas, Alicia; Luque-Escamilla, Pedro L.; Majumdar, P.; Makariev, M.; Mandát, Dušan; Manganaro, Marina; Mannheim, K.; Mariotti, M.; Marquez, Patricia; Marsella, G.; Martı́, Josep; Martinez, Oibar; Martínez, G.; Martı́nez, M.; Marusevec, Petra; Mas, Alvaro; Maurin, G.; Mazin, D.; Miranda, D. Medina; Guillen, Enrique Mestre; Mićanović, Saša; Miceli, Davide; Miener, Tjark; Miranda, Jose Miguel; Mirzoyan, R.; Mizuno, T.; Molina, Edgar; Montaruli, T.; Monteiro, Inocencio; Moralejo, A.; Morcuende, Daniel; Moretti, E.; Morselli, A.; Mrakovcic, Karlo; Murase, Kohta; Nagai, A.; Nakamori, Takeshi; Nickel, Lukas; Nieto, D.; Nievas, Mireia; Nishijima, K.; Noda, K.; Nosek, D.; Nöthe, Maximilian; Nozaki, Seiya; Ohishi, M.; Ohtani, Yoshiki; Oka, Tomohiko; Okazaki, N.; Okumura, A.; Orito, R.; Otero-Santos, Jorge; Palatiello, M.; Paneque, D.; Paoletti, R.; Paredes, J. M.; Pavletić, Lovro; Pech, M.; Pecimotika, Mario; Poireau, V.; Polo, Miguel Angel Molinero; Prandini, E.; Prast, J.; Priyadarshi, Chaitanya; Prouza, M.; Rando, R.; Rhode, W.; Ribó, M.; Rizi, Vincenzo; Rugliancich, A.; Ruíz, José Enrique; Saito, Takayuki; Sakurai, Shunsuke; Sánchez, David; Šarić, Toni; Saturni, Francesco Gabriele; Scherpenberg, Juliane van; Schleicher, Bernd; Schubert, Jan Lukas; Schüßler, F.; Schweizer, T.; Arroyo, Monica Seglar; Shellard, R. C.; Sitarek, J.; Sliusar, Vitalii; Spolon, Alessia; Strišković, Jelena; Strzys, M.; Suda, Y.; Sunada, Yuji; Tajima, H.; Takahashi, Mitsunari; Takahashi, H.; Takata, Jumpei; Takeishi, Ryuji; Tam, Pak-Hin Thomas; Tanaka, Shuta J.; Tateishi, Dai; Tejedor, Luis; Temnikov, P.; Terada, Y.; Terzić, T.; Teshima, M.; Tluczykont, M.; Tokanai, Fuyuki; Torres, D. F.; Trávničék, P.; Truzzi, Stefano; Vacula, Martin; Acosta, Mónica Vázquez; Verguilov, V.; Verna, Gaia; Viale, Ilaria; Vigorito, C.; Vitale, V.; Vovk, Ievgen; Vuillaume, Thomas; Walter, R.; Will, Martin; Yamamoto, Tokonatsu; Yamazaki, Ryo; Yoshida, Tatsuo; Yoshikoshi, T.; Zarić, Darko

doi:10.22323/1.395.0771

Cited by 1 publication

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The TRN model are trained and tested with a modest cut, adapted from Ref. [14], where faint images (Hillas intensity less than 50 photoelectrons) and images close to the camera edge (leakage2 parameter more than 0.2) are discarded. For the stereoscopic reconstruction, faint and truncated images are kept, but a multiplicity cut of four or more triggered telescopes is applied.…”

Section: Data Selection (Quality Cuts)mentioning

confidence: 99%

“…Previous works have demonstrated the potential application of these algorithms for IACT event reconstruction [8][9][10][11][12][13]. DCN-based monoscopic telescope performance and the application of DCNs on observational data from the first Large-Sized Telescope (LST-1 prototype) of CTA North is discussed in these proceedings elsewhere [14,15]. As a natural continuation of this line of work, this contribution focuses on full-event reconstruction of MC-simulated stereoscopic events.…”

Section: Introductionmentioning

confidence: 99%

“…Y. Yamane 141 , R. Yamazaki 209 , S. Yanagita 176 , L. Yang 205 , S. Yoo 180 , T. Yoshida 176 , T. Yoshikoshi 2 , P. Yu 71 , P. Yu 85 , A. Yusafzai 59 , M. Zacharias 20 , G. Zaharĳas 68 , B. Zaldivar 14 , L. Zampieri 76 , R. Zanmar Sanchez 29 , D. Zaric 150 , M. Zavrtanik 68 , D. Zavrtanik 68 , A.A. Zdziarski 49 , A. Zech 20 , H. Zechlin 64 , A. Zenin 139 , A. Zerwekh 35 , V.I. Zhdanov 136 , K. Ziętara 169 , A. Zink 142 , J. Ziółkowski 49 , V. Zitelli 21…”

mentioning

confidence: 99%

See 2 more Smart Citations

Reconstruction of stereoscopic CTA events using deep learning with CTLearn

Miener¹,

Nieto²,

Brill³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The Cherenkov Telescope Array (CTA), conceived as an array of tens of imaging atmospheric Cherenkov telescopes (IACTs), is an international project for a next-generation ground-based gamma-ray observatory, aiming to improve on the sensitivity of current-generation instruments a factor of five to ten and provide energy coverage from 20 GeV to more than 300 TeV. Arrays of IACTs probe the very-high-energy gamma-ray sky. Their working principle consists of the simultaneous observation of air showers initiated by the interaction of very-high-energy gamma rays and cosmic rays with the atmosphere. Cherenkov photons induced by a given shower are focused onto the camera plane of the telescopes in the array, producing a multi-stereoscopic record of the event. This image contains the longitudinal development of the air shower, together with its spatial, temporal, and calorimetric information. The properties of the originating veryhigh-energy particle (type, energy, and incoming direction) can be inferred from those images by reconstructing the full event using machine learning techniques. In this contribution, we present a purely deep-learning driven, full-event reconstruction of simulated, stereoscopic IACT events using CTLearn. CTLearn is a package that includes modules for loading and manipulating IACT data and for running deep learning models, using pixel-wise camera data as input.

show abstract

Section: Data Selection (Quality Cuts)mentioning

confidence: 99%