Event reconstruction for KM3NeT/ORCA using convolutional neural networks

• Published in: Journal of Instrumentation
• Main Authors: Aiello, S., Albert, A., Garre, S. Alves, Aly, Z., Ameli, F., Andre, M., Androulakis, G., Anghinolfi, M., Anguita, M., Anton, G., Ardid Ramírez, Miguel, Aublin, J., Bagatelas, C., Barbarino, G., Baret, B., Diego-Tortosa, D., Espinosa Roselló, Víctor, Martínez Mora, Juan Antonio, Poirè, Chiara
• Other Authors: Universitat Politècnica de València. Departamento de Física Aplicada - Departament de Física Aplicada, Universitat Politècnica de València. Instituto de Investigación para la Gestión Integral de Zonas Costeras - Institut d'Investigació per a la Gestió Integral de Zones Costaneres, European Commission, Junta de Andalucía, GENERALITAT VALENCIANA, Deutsche Forschungsgemeinschaft, Agencia Estatal de investigación, Institut Universitaire de France, National Science Centre, Polonia, European Regional Development Fund, Instituto Nazionale di Fisica Nucleare, Agence Nationale de la Recherche, Francia, Shota Rustaveli National Science Foundation, Netherlands Organization for Scientific Research, Ministerio de Ciencia, Innovación y Universidades, National Authority for Scientific Research, Rumanía, General Secretariat for Research and Technology, Grecia, Fundació Bancària Caixa d'Estalvis i Pensions de Barcelona, Ministero dell'Istruzione dell'Università e della Ricerca, Italia, Ministère de l'Education Nationale, de la Formation professionnelle, de l'Enseignement Supérieur et de la Recherche Scientifique, Marruecos
• Format: Article in Journal/Newspaper
• Language: English
• Published: IOP Publishing 2020
• Subjects: hist; psy; Orca
• Online Access: https://doi.org/10.1088/1748-0221/15/10/P10005; http://hdl.handle.net/10251/170281

S Breiman, L. (2001). Machine Learning, 45(1), 5-32. doi:10.1023/a:1010933404324 [EN] 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. The authors acknowledge the financial support of the funding agencies: Agence Nationale de la Recherche (contract ANR-15-CE31-0020), Centre National de la Recherche Scientifique (CNRS), Commission Europeenne (FEDER fund and Marie Curie Program), Institut Universitaire de France (IUF), LabEx UnivEarthS (ANR-10-LABX-0023 and ANR-18-IDEX-0001), Paris Ile-de-France Region, France; Shota Rustaveli National Science Foundation of Georgia (SRNSFG, FR-18-1268), ...