Event reconstruction for KM3NeT/ORCA using convolutional neural networks

S. Aiello (1) , A. Albert (2, 3) , S. Alves Garre , Z. Aly (4) , F. Ameli , M. Andre , G. Androulakis , M. Anghinolfi , M. Anguita , G. Anton , M. Ardid , J. Aublin (5) , C. Bagatelas , G. Barbarino , B. Baret (5) , S. Basegmez Du Pree , M. Bendahman , E. Berbee , A.M. van den Berg , V. Bertin (4) , S. Biagi , A. Biagioni , M. Bissinger , M. Boettcher , J. Boumaaza , M. Bouta , M. Bouwhuis , C. Bozza , H. Brânzaş , R. Bruijn , J. Brunner (4) , E. Buis , R. Buompane , J. Busto (4) , B. Caiffi , D. Calvo , A. Capone , V. Carretero , P. Castaldi , S. Celli , M. Chabab , N. Chau (5) , A. Chen , S. Cherubini , V. Chiarella , T. Chiarusi , M. Circella , R. Cocimano , J.A.B. Coelho (5) , A. Coleiro (5) , M. Colomer Molla (5) , R. Coniglione , P. Coyle (4) , A. Creusot (5) , G. Cuttone , A. d'Onofrio , R. Dallier (6) , M. de Palma , I. Di Palma , A.F. Díaz , D. Diego-Tortosa , C. Distefano , A. Domi (4) , R. Donà , C. Donzaud (5) , D. Dornic (4) , M. Dörr , D. Drouhin (7, 2) , T. Eberl , A. Eddyamoui , T. van Eeden , D. van Eijk , I. El Bojaddaini , D. Elsaesser , A. Enzenhöfer (4) , V. Espinosa Roselló , P. Fermani , G. Ferrara , M.D. Filipović , F. Filippini , L.A. Fusco (5) , O. Gabella (8) , T. Gal , A. Garcia Soto , F. Garufi , Y. Gatelet (5) , N. Geisselbrecht , L. Gialanella , E. Giorgio , S.R. Gozzini , R. Gracia , K. Graf , D. Grasso , G. Grella , D. Guderian , C. Guidi , S. Hallmann , H. Hamdaoui , H. van Haren , A. Heijboer , A. Hekalo , J.J. Hernández-Rey , J. Hofestädt , F. Huang (7) , W. Idrissi Ibnsalih , G. Illuminati , C.W. James , M. de Jong , P. de Jong , B.J. Jung , M. Kadler , P. Kalaczyński , O. Kalekin , U.F. Katz , N.R Khan Chowdhury , G. Kistauri , F. van Der Knaap , E.N. Koffeman , P. Kooijman , A. Kouchner (5, 9) , M. Kreter , V. Kulikovskiy , R. Lahmann , G. Larosa , R. Le Breton (5) , O. Leonardi , F. Leone , E. Leonora , G. Levi , M. Lincetto (4) , M. Lindsey Clark (5) , T. Lipreau (6) , A. Lonardo , F. Longhitano , D. Lopez-Coto , L. Maderer (5) , J. Mańczak , K. Mannheim , A. Margiotta , A. Marinelli , C. Markou , L. Martin (6) , J.A. Martínez-Mora , A. Martini , F. Marzaioli , S. Mastroianni , S. Mazzou , K.W. Melis , G. Miele , P. Migliozzi , E. Migneco , P. Mijakowski , L.S. Miranda , C.M. Mollo , M. Morganti , M. Moser , A. Moussa , R. Muller , M. Musumeci , L. Nauta , S. Navas , C.A. Nicolau , B. Ó Fearraigh , M. Organokov (7) , A. Orlando , G. Papalashvili , R. Papaleo , C. Pastore , A.M. Păun , G.E. Păvălaş , C. Pellegrino , M. Perrin-Terrin (4) , P. Piattelli , C. Pieterse , K. Pikounis , O. Pisanti , C. Poirè , V. Popa , M. Post , T. Pradier (7) , G. Pühlhofer , S. Pulvirenti , O. Rabyang , F. Raffaelli , N. Randazzo , A. Rapicavoli , S. Razzaque , D. Real , S. Reck , G. Riccobene , M. Richer (7) , S. Rivoire (8) , A. Rovelli , F. Salesa Greus , D.F.E. Samtleben , A. Sánchez Losa , M. Sanguineti , A. Santangelo , D. Santonocito , P. Sapienza , J. Schnabel , J. Seneca , I. Sgura , R. Shanidze , A. Sharma , F. Simeone , A. Sinopoulou , B. Spisso , M. Spurio , D. Stavropoulos , J. Steijger , S.M. Stellacci , M. Taiuti , Y. Tayalati , E. Tenllado , T. Thakore , S. Tingay , E. Tzamariudaki , D. Tzanetatos , V. van Elewyck (5, 9) , G. Vannoye , George Vasileiadis (8) , F. Versari , S. Viola , D. Vivolo , G. de Wasseige (5) , J. Wilms , R. Wojaczyński , E. de Wolf , D. Zaborov (4) , S. Zavatarelli , A. Zegarelli , D. Zito , J.D. Zornoza , J. Zúñiga , N. Zywucka

1 INFN - Istituto Nazionale di Fisica Nucleare
2 GRPHE - Groupe de Recherche en Physique des Hautes Energies
3 IN2P3 - Institut National de Physique Nucléaire et de Physique des Particules du CNRS
4 CPPM - Centre de Physique des Particules de Marseille
5 APC (UMR_7164) - AstroParticule et Cosmologie
6 SUBATECH - Laboratoire de physique subatomique et des technologies associées
7 IPHC - Institut Pluridisciplinaire Hubert Curien
8 LUPM - Laboratoire Univers et Particules de Montpellier
9 IUF - Institut universitaire de France

The KM3NeT research infrastructure is currently under construction at two locations in the Mediterranean Sea. The KM3NeT/ORCA water-Cherenkov neutrino detector off the French coast will instrument several megatons of seawater with photosensors. Its main objective is the determination of the neutrino mass ordering. This work aims at demonstrating the general applicability of deep convolutional neural networks to neutrino telescopes, using simulated datasets for the KM3NeT/ORCA detector as an example. To this end, the networks are employed to achieve reconstruction and classification tasks that constitute an alternative to the analysis pipeline presented for KM3NeT/ORCA in the KM3NeT Letter of Intent. They are used to infer event reconstruction estimates for the energy, the direction, and the interaction point of incident neutrinos. The spatial distribution of Cherenkov light generated by charged particles induced in neutrino interactions is classified as shower- or track-like, and the main background processes associated with the detection of atmospheric neutrinos are recognized. Performance comparisons to machine-learning classification and maximum-likelihood reconstruction algorithms previously developed for KM3NeT/ORCA are provided. It is shown that this application of deep convolutional neural networks to simulated datasets for a large-volume neutrino telescope yields competitive reconstruction results and performance improvements with respect to classical approaches.

Mots clés: Cherenkov detectors; Large detector systems for particle and astroparticle physics; Neutrino detectors; Performance of High Energy Physics Detectors; neutrino: detector; neutrino: interaction; neutrino: atmosphere; neutrino: mass; radiation: Cherenkov; vertex: primary; KM3NeT; neural network; Cherenkov counter: water; performance; spatial distribution; charged particle; photomultiplier; background; network

Domaines: Instrumentations et Détecteurs [physics.ins-det]

S. Aiello, A. Albert, S. Alves Garre, Z. Aly, F. Ameli, et al.. Event reconstruction for KM3NeT/ORCA using convolutional neural networks. JINST, 2020, 15 (10), pp.P10005. ⟨10.1088/1748-0221/15/10/P10005⟩. ⟨hal-03178773⟩