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.

Event reconstruction for KM3NeT/ORCA using convolutional neural networks

Castaldi, P.;Filippini, F.;Fusco, L. A.;Illuminati, G.;Levi, G.;Margiotta, A.;Pellegrino, C.;Spurio, M.;Versari, F.;
2020

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.
JOURNAL OF INSTRUMENTATION
Aiello, S.; Albert, A.; Garre, S. Alves; Aly, Z.; Ameli, F.; Andre, M.; Androulakis, G.; Anghinolfi, M.; Anguita, M.; Anton, G.; Ardid, M.; Aublin, J.; Bagatelas, C.; Barbarino, G.; Baret, B.; Pree, S. Basegmez du; Bendahman, M.; Berbee, E.; van den Berg, A.M.; Bertin, V.; Biagi, S.; Biagioni, A.; Bissinger, M.; Boettcher, M.; Boumaaza, J.; Bouta, M.; Bouwhuis, M.; Bozza, C.; Brânzaş, H.; Bruijn, R.; Brunner, J.; Buis, E.; Buompane, R.; Busto, J.; Caiffi, B.; Calvo, D.; Capone, A.; Carretero, V.; Castaldi, P.; Celli, S.; Chabab, M.; Chau, N.; Chen, A.; Cherubini, S.; Chiarella, V.; Chiarusi, T.; Circella, M.; Cocimano, R.; Coelho, J.A.B.; Coleiro, A.; Molla, M. Colomer; Coniglione, R.; Coyle, P.; Creusot, A.; Cuttone, G.; D'Onofrio, A.; Dallier, R.; Palma, M. De; Palma, I. Di; Díaz, A.F.; Diego-Tortosa, D.; Distefano, C.; Domi, A.; Donà, R.; Donzaud, C.; Dornic, D.; Dörr, M.; Drouhin, D.; Eberl, T.; Eddyamoui, A.; Eeden, T. van; Eijk, D. van; Bojaddaini, I. El; Elsaesser, D.; Enzenhöfer, A.; Roselló, V. Espinosa; Fermani, P.; Ferrara, G.; Filipović, M. D.; Filippini, F.; Fusco, L.A.; Gabella, O.; Gal, T.; Soto, A. Garcia; Garufi, F.; Gatelet, Y.; Geißelbrecht, N.; Gialanella, L.; Giorgio, E.; Gozzini, S.R.; Gracia, R.; Graf, K.; Grasso, D.; Grella, G.; Guderian, D.; Guidi, C.; Hallmann, S.; Hamdaoui, H.; Haren, H. van; Heijboer, A.; Hekalo, A.; Hernández-Rey, J.J.; Hofestädt, J.; Huang, F.; Ibnsalih, W. Idrissi; Illuminati, G.; James, C.W.; de Jong, M.; de Jong, P.; Jung, B.J.; Kadler, M.; Kalaczyński, P.; Kalekin, O.; Katz, U.F.; Chowdhury, N.R Khan; Kistauri, G.; Knaap, F. van der; Koffeman, E.N.; Kooijman, P.; Kouchner, A.; Kreter, M.; Kulikovskiy, V.; Lahmann, R.; Larosa, G.; Breton, R. Le; Leonardi, O.; Leone, F.; Leonora, E.; Levi, G.; Lincetto, M.; Clark, M. Lindsey; Lipreau, T.; Lonardo, A.; Longhitano, F.; Lopez-Coto, D.; Maderer, L.; Mańczak, J.; Mannheim, K.; Margiotta, A.; Marinelli, A.; Markou, C.; Martin, L.; Martínez-Mora, J.A.; Martini, A.; Marzaioli, F.; Mastroianni, S.; Mazzou, S.; Melis, K.W.; Miele, G.; Migliozzi, P.; Migneco, E.; Mijakowski, P.; Miranda, L.S.; Mollo, C.M.; Morganti, M.; Moser, M.; Moussa, A.; Muller, R.; Musumeci, M.; Nauta, L.; Navas, S.; Nicolau, C.A.; Ó Fearraigh, B.; Organokov, M.; Orlando, A.; Papalashvili, G.; Papaleo, R.; Pastore, C.; Păun, A. M.; Păvălaş, G.E.; Pellegrino, C.; Perrin-Terrin, M.; Piattelli, P.; Pieterse, C.; Pikounis, K.; Pisanti, O.; Poirè, C.; Popa, V.; Post, M.; Pradier, T.; Pühlhofer, 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, F. Salesa; Samtleben, D.F.E.; Sánchez Losa, A.; Sanguineti, M.; Santangelo, A.; Santonocito, D.; Sapienza, P.; Schnabel, J.; Seneca, J.; Sgura, I.; Shanidze, R.; Sharma, A.; Simeone, F.; Sinopoulou, A.; Spisso, B.; Spurio, M.; Stavropoulos, D.; Steijger, J.; Stellacci, S.M.; Taiuti, M.; Tayalati, Y.; Tenllado, E.; Thakore, T.; Tingay, S.; Tzamariudaki, E.; Tzanetatos, D.; Elewyck, V. Van; Vannoye, G.; Vasileiadis, G.; Versari, F.; Viola, S.; Vivolo, D.; de Wasseige, G.; Wilms, J.; Wojaczyński, R.; de Wolf, E.; Zaborov, D.; Zavatarelli, S.; Zegarelli, A.; Zito, D.; Zornoza, J.D.; Zúñiga, J.; Zywucka, N.
File in questo prodotto:
File Dimensione Formato  
Aiello_2020_J._Inst._15_P10005.pdf

accesso aperto

Tipo: Versione (PDF) editoriale
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 2.6 MB
Formato Adobe PDF
2.6 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11585/774385
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact