NUK - logo
E-viri
Celotno besedilo
Odprti dostop
  • A Convolutional Neural Network for Multiple Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
    collaboration, MicroBooNE; Abratenko, P; Alrashed, M; R An; Anthony, J; Ashkenazi, A; Balasubramanian, S; Baller, B; Bathe-Peters, L; Berkman, S; Bolton, T; Caratelli, D; R Castillo Fernandez; Cerati, G; Conrad, J M; Convery, M; Cooper-Troendle, L; Crespo-Anadon, J I; Duffy, K; Eberly, B; Ereditato, A; Evans, J J; Fitzpatrick, R S; Furmanski, A P; G Ge; Gollapinni, S; Gramellini, E; Green, P; W Gu; Guenette, R; Hagaman, L; Hamilton, P; Hen, O; Horton-Smith, G A; Itay, R; James, C; de Vries, J Jan; Jiang, L; Johnson, R A; Jwa, Y J; Ketchum, W; Kobilarcik, T; Kreslo, I; Lepetic, I; Y Li; Lorca, D; Louis, W C; Mariani, C; Marsden, D; Marshall, J; Martin-Albo, J; Mason, K; Mastbaum, A; McConkey, N; Mistry, K; Mooney, M; Moore, C D; Mousseau, J; Naples, D; Papadopoulou, A; Papavassiliou, V; Paudel, A; Piasetzky, E; Qian, X; Radeka, V; Reggiani-Guzzo, M; Ren, L; Rochester, L; J Rodriguez Rondon; Rogers, H E; Russell, B; Scanavini, G; Schukraft, A; Sinclair, J; Smith, A; Snider, E L; Soldner-Rembold, S; Soleti, S R; Spentzouris, P; Spitz, J; Stancari, M; J St John; Strauss, T; Sutton, K; Sword-Fehlberg, S; Szelc, A M; Tagg, N; Thorpe, C; Toups, M; Y -T Tsai; Usher, T; Weber, M; Wei, H; Williams, Z; Wolbers, S; Yandel, E; Yang, T; Yates, L E; Zennamo, J; Zhang, C

    arXiv.org, 03/2021
    Paper, Journal Article

    We present the multiple particle identification (MPID) network, a convolutional neural network (CNN) for multiple object classification, developed by MicroBooNE. MPID provides the probabilities of \(e^-\), \(\gamma\), \(\mu^-\), \(\pi^\pm\), and protons in a single liquid argon time projection chamber (LArTPC) readout plane. The network extends the single particle identification network previously developed by MicroBooNE. MPID takes as input an image either cropped around a reconstructed interaction vertex or containing only activity connected to a reconstructed vertex, therefore relieving the tool from inefficiencies in vertex finding and particle clustering. The network serves as an important component in MicroBooNE's deep learning based \(\nu_e\) search analysis. In this paper, we present the network's design, training, and performance on simulation and data from the MicroBooNE detector.

Vnos na polico