학술논문

Event reconstruction for KM3NeT/ORCA using convolutional neural networks
Document Type
Working Paper
Author
Aiello, SebastianoAlbert, ArnauldGarre, Sergio AlvesAly, ZinebAmeli, FabrizioAndre, MichelAndroulakis, GiorgosAnghinolfi, MarcoAnguita, ManciaAnton, GiselaArdid, MiquelAublin, JulienBagatelas, ChristosBarbarino, GiancarloBaret, BrunyPree, Suzan Basegmez duBendahman, MeriemBerbee, EdwardBertin, VincentBiagi, SimoneBiagioni, AndreaBissinger, MatthiasBoettcher, MarkusBoumaaza, JihadBouta, MohammedBouwhuis, MiekeBozza, CristianoBranzas, HoreaBruijn, RonaldBrunner, JürgenBuis, Ernst-JanBuompane, RaffaeleBusto, JoseCaiffi, BarbaraCalvo, DavidCapone, AntonioCarretero, VíctorCastaldi, PaoloCelli, SilviaChabab, MohamedChau, NhanChen, AndrewCherubini, SilvioChiarella, VitalianoChiarusi, TommasoCircella, MarcoCocimano, RosannaCoelho, JoaoColeiro, AlexisMolla, Marta ColomerConiglione, RosaCoyle, PaschalCreusot, AlexandreCuttone, GiacomoD'Onofrio, AntonioDallier, Richardde Jong, Maartende Jong, PaulDe Palma, Maurode Wasseige, Gwenhaëlde Wolf, ElsDi Palma, IreneDiaz, AntonioDiego-Tortosa, DídacDistefano, CarlaDomi, AlbaDonà, RobertoDonzaud, CorinneDornic, DamienDörr, ManuelDrouhin, DorianeEberl, ThomasBojaddaini, Imad ElElsaesser, DominikEnzenhöfer, AlexanderFermani, PaoloFerrara, GiovannaFilipovic, MiroslavFilippini, FrancescoFusco, Luigi AntonioGabella, OmarGal, TamasSoto, Alfonso Andres GarciaGarufi, FabioGatelet, YoannGeißelbrecht, NicoleGialanella, LucioGiorgio, EmidioGozzini, Sara RebeccaGracia, RodrigoGraf, KayGrasso, DarioGrella, GiuseppeGuidi, CarloHallmann, SteffenHamdaoui, HassaneHeijboer, AartHekalo, AmarHernandez-Rey, Juan-JoseHofestädt, JannikHuang, FeifeiIbnsalih, Walid IdrissiIlluminati, GiuliaJames, ClancyJung, Bouke JisseKadler, MatthiasKalaczyński, PiotrKalekin, OlegKatz, UliChowdhury, Nafis Rezwan KhanKistauri, GiorgiKoffeman, ElsKooijman, PaulKouchner, AntoineKreter, MichaelKulikovskiy, VladimirLahmann, RobertLarosa, GiuseppinaBreton, Remy LeLeonardi, OrnellaLeone, FrancescoLeonora, EmanueleLevi, GiuseppeLincetto, MassimilianoClark, Miles LindseyLipreau, ThomasLonardo, AlessandroLonghitano, FabioCoto, Daniel LopezMaderer, LukasMańczak, JerzyMannheim, KarlMargiotta, AnnaritaMarinelli, AntonioMarkou, ChristosMartin, LilianMartínez-Mora, Juan AntonioMartini, AgneseMarzaioli, FabioMastroianni, StefanoMazzou, SafaaMelis, KarelMiele, GennaroMigliozzi, PasqualeMigneco, EmilioMijakowski, PiotrPalacios, Luis Salvador MirandaMollo, Carlos MaximilianoMorganti, MauroMoser, MichaelMoussa, AbdelilahMuller, RasaMusumeci, MarioNauta, LodewijkNavas, SergioNicolau, Carlo AlessandroFearraigh, Brían ÓOrganokov, MukharbekOrlando, AngeloPapalashvili, GogitaPapaleo, RiccardoPastore, CosimoPaun, AlicePavalas, Gabriela EmiliaPellegrino, CarmeloPerrin-Terrin, MathieuPiattelli, PaoloPieterse, CamielPikounis, KonstantinosPisanti, OfeliaPoirè, ChiaraPopa, VladPost, MaartenPradier, ThierryPühlhofer, GerdPulvirenti, SaraRabyang, OmphileRaffaelli, FabrizioRandazzo, NunzioRapicavoli, AntonioRazzaque, SoeburReal, DiegoReck, StefanRiccobene, GiorgioRicher, MarcRivoire, StephaneRovelli, AlbertoGreus, Francisco SalesaSamtleben, Dorothea Franziska ElisabethLosa, Agustín SánchezSanguineti, MatteoSantangelo, AndreaSantonocito, DomenicoSapienza, PieraSchnabel, JuttaSeneca, JordanSgura, IreneShanidze, RezoSharma, AnkurSimeone, FrancescoSinopoulou, AnnaSpisso, BernardinoSpurio, MaurizioStavropoulos, DimitrisSteijger, JosStellacci, Simona MariaTaiuti, MauroTayalati, YahyaTenllado, EnriqueThakore, TarakTingay, StevenTzamariudaki, EkateriniTzanetatos, DimitriosBerg, Ad van denvan der Knaap, Fritsvan Eijk, DaanVan Elewyck, Véroniquevan Haren, HansVannoye, GodefroyVasileiadis, GeorgeVersari, FedericoViola, SalvatoreVivolo, DanieleWilms, JoernWojaczyński, RafałZaborov, DmitryZavatarelli, SandraZegarelli, AngelaZito, DanieleZornoza, Juan-de-DiosZúñiga, JuanZywucka, Natalia
Source
JINST 15 P10005 (2020)
Subject
Astrophysics - Instrumentation and Methods for Astrophysics
High Energy Physics - Experiment
Physics - Instrumentation and Detectors
Language
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.