Ítem


Background rejection in NEXT using deep neural networks

We investigate the potential of using deep learning techniques to reject background events in searches for neutrinoless double beta decay with high pressure xenon time projection chambers capable of detailed track reconstruction. The differences in the topological signatures of background and signal events can be learned by deep neural networks via training over many thousands of events. These networks can then be used to classify further events as signal or background, providing an additional background rejection factor at an acceptable loss of efficiency. The networks trained in this study performed better than previous methods developed based on the use of the same topological signatures by a factor of 1.2 to 1.6, and there is potential for further improvement

Institute of Physics (IOP)

Autor: Renner, Joshua
Farbin, A.
Muñoz Vidal, J.
Benlloch Rodríguez, J.M.
Botas, A.
Ferrario, Paola
Gómez Cadenas, Juan José
Álvarez Puerta, Vicente
Azevedo, C.D.R.
Borges, Filipa I.G.M.
Cárcel García, Sara
Carrión, J. V.
Cebrián, Susana
Cervera Villanueva, Anselmo
Conde, Carlos A.N.
Díaz Medina, José
Diesburg, M.
Esteve, Raúl
Fernandes, L.M.P.
Ferreira, Antonio Luis
Freitas, Elisabete D.C.
Goldschmidt, Azriel
González-Díaz, Diego
Gutiérrez, Rafael María
Hauptman, John M.
Henriques, C.A.O.
Hernando Morata, J.A.
Herrero, Vicente
Jones, B.
Labarga, Luis A.
Laing, Andrew
Lebrun, P.
Liubarsky, Igor
López-March, N.
Lorca Galindo, David
Losada, Marta
Martín-Albo Simón, Justo
Martínez Lema, Gonzalo
Martínez Pérez, Alberto
Monrabal Capilla, Francesc
Monteiro, Cristina M.B.
Mora, Francisco José
Moutinho, L.M.
Nebot Guinot, Miquel
Novella, P.
Nygren, David R.
Palmeiro, B.
Para, A.
Pérez, Javier Martin
Querol, M.
Ripoll Masferrer, Lluís
Rodríguez Samaniego, Javier
Santos, Filomena P.
dos Santos, Joaquim M.F.
Serra Díaz-Cano, Luis
Shuman, Derek B.
Simón Estévez, Ander
Sofka, C.
Sorel, Michel
Toledo, J.F.
Torrent Collell, Jordi
Tsamalaidze, Zviadi
Veloso, João F.C.A.
White, James T.
Webb, R.C.
Yahlali Haddou, Nadia
Yepes-Ramírez, H.
Data: 15 febrer 2020
Resum: We investigate the potential of using deep learning techniques to reject background events in searches for neutrinoless double beta decay with high pressure xenon time projection chambers capable of detailed track reconstruction. The differences in the topological signatures of background and signal events can be learned by deep neural networks via training over many thousands of events. These networks can then be used to classify further events as signal or background, providing an additional background rejection factor at an acceptable loss of efficiency. The networks trained in this study performed better than previous methods developed based on the use of the same topological signatures by a factor of 1.2 to 1.6, and there is potential for further improvement
Accés al document: http://hdl.handle.net/2072/372840
Llenguatge: eng
Editor: Institute of Physics (IOP)
Drets: Attribution 3.0 Spain
URI Drets: http://creativecommons.org/licenses/by/3.0/es/
Matèria: Enginyeria -- Instruments
Engineering instruments
Anàlisi de conglomerats
Cluster analysis
Títol: Background rejection in NEXT using deep neural networks
Tipus: info:eu-repo/semantics/article
Repositori: Recercat

Matèries

Autors