Event reconstruction for KM3NeT/ORCA using convolutional neural networks

Aiello S, Albert A, Garre SA, Aly Z, Ameli F, Andre M, Androulakis G, Anghinolfi M, Anguita M, Anton G, Ardid M, Aublin J, Bagatelas C, Barbarino G, Baret B, Du Pree SB, Bendahman M, Berbee E, Van Den Berg AM, Bertin , Biagi S, Biagioni A, Bissinger M, Boettcher M, Boumaaza J, Bouta M, Bouwhuis M, Bozza C, Branzas H, Bruijn R, Brunner J, Buis E, Buompane R, Busto J, Caiffi B, Calvo D, Capone A, Carretero , Castaldi P, Celli S, Chabab M, Chau N, Chen A, Cherubini S, Chiarella , Chiarusi T, Circella M, Cocimano R, Coelho JAB, Coleiro A, Molla MC, Coniglione R, Coyle P, Creusot A, Cuttone G, D'Onofrio A, Dallier R, De Palma M, Di Palma , Diaz AF, Diego-Tortosa D, Distefano C, Domi A, Dona R, Donzaud C, Dornic D, Dorr M, Drouhin D, Eberl T, Eddyamoui A, Van Eeden T, Van Eijk D, El Bojaddaini , Elsaesser D, Enzenhofer A, Rosello VE, Fermani P, Ferrara G, Filipovic MD, Filippini F, Fusco LA, Gabella O, Gal T, Soto AG, Garufi F, Gatelet Y, Geißelbrecht N, Gialanella L, Giorgio E, Gozzini SR, Gracia R, Graf K, Grasso D, Grella G, Guderian D, Guidi C, Hallmann S, Hamdaoui H, Van Haren H, Heijboer A, Hekalo A, Hernandez-Rey JJ, Hofestadt J, Huang F, Ibnsalih WI, Illuminati G, James CW, De Jong M, De Jong P, Jung BJ, Kadler M, Kalaczynski P, Kalekin O, Katz U, Chowdhury NRK, Kistauri G, Van Der Knaap F, Koffeman EN, Kooijman P, Kouchner A, Kreter M, Kulikovskiy , Lahmann R, Larosa G, Le Breton R, Leonardi O, Leone F, Leonora E, Levi G, Lincetto M, Clark ML, Lipreau T, Lonardo A, Longhitano F, Lopez-Coto D, Maderer L, Manczak J, Mannheim K, Margiotta A, Marinelli A, Markou C, Martin L, Martinez-Mora JA, Martini A, Marzaioli F, Mastroianni S, Mazzou S, Melis KW, Miele G, Migliozzi P, Migneco E, Mijakowski P, Miranda LS, Mollo CM, Morganti M, Moser M, Moussa A, Muller R, Musumeci M, Nauta L, Navas S, Nicolau CA, Fearraigh BO, Organokov M, Orlando A, Papalashvili G, Papaleo R, Pastore C, Paun AM, Pavalas GE, Pellegrino C, Perrin-Terrin M, Piattelli P, Pieterse C, Pikounis K, Pisanti O, Poire C, Popa , Post M, Pradier T, Puhlhofer G, Pulvirenti S, Rabyang O, Raffaelli F, Randazzo N, Rapicavoli A, Razzaque S, Real D, Reck S, Riccobene G, Richer M, Rivoire S, Rovelli A, Greus FS, Samtleben DFE, Losa AS, Sanguineti M, Santangelo A, Santonocito D, Sapienza P, Schnabel J, Seneca J, Sgura , Shanidze R, Sharma A, Simeone F, Sinopoulou A, Spisso B, Spurio M, Stavropoulos D, Steijger J, Stellacci SM, Taiuti M, Tayalati Y, Tenllado E, Thakore T, Tingay S, Tzamariudaki E, Tzanetatos D, Van Elewyck V, Vannoye G, Vasileiadis G, Versari F, Viola S, Vivolo D, De Wasseige G, Wilms J, Wojaczynski R, De Wolf E, Zaborov D, Zavatarelli S, Zegarelli A, Zito D, Zornoza JD, Zuniga J, Żywucka N (2020)


Publication Type: Journal article

Publication year: 2020

Journal

Book Volume: 15

Journal Issue: 10

DOI: 10.1088/1748-0221/15/10/P10005

Abstract

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.

Authors with CRIS profile

How to cite

APA:

Aiello, S., Albert, A., Garre, S.A., Aly, Z., Ameli, F., Andre, M.,... Żywucka, N. (2020). Event reconstruction for KM3NeT/ORCA using convolutional neural networks. Journal of Instrumentation, 15(10). https://doi.org/10.1088/1748-0221/15/10/P10005

MLA:

Aiello, S., et al. "Event reconstruction for KM3NeT/ORCA using convolutional neural networks." Journal of Instrumentation 15.10 (2020).

BibTeX: Download