E-viri
PDF
Recenzirano
Odprti dostop
-
Abratenko, P.; An, R.; Asaadi, J.; Ashkenazi, A.; Balasubramanian, S.; Baller, B.; Barnes, C.; Barr, G.; Berkman, S.; Bhanderi, A.; Bishai, M.; Caro Terrazas, I.; Castillo Fernandez, R.; Chen, Y.; Church, E.; Cianci, D.; Conrad, J. M.; Convery, M.; Cooper-Troendle, L.; Crespo-Anadón, J. I.; Del Tutto, M.; Domine, L.; Dytman, S.; Eberly, B.; Ereditato, A.; Evans, J. J.; Fiorentini Aguirre, G. A.; Gardiner, S.; Ge, G.; Gramellini, E.; Green, P.; Greenlee, H.; Hall, E.; Hen, O.; Horton-Smith, G. A.; Hourlier, A.; Itay, R.; Jan de Vries, J.; Jo, J. H.; Jwa, Y.-J.; Kamp, N.; Karagiorgi, G.; Ketchum, W.; Kirby, B.; Kirby, M.; Kobilarcik, T.; Kreslo, I.; LaZur, R.; Li, K.; Li, Y.; Littlejohn, B. R.; Lorca, D.; Louis, W. C.; Luo, X.; Marchionni, A.; Mariani, C.; Marshall, J.; Martin-Albo, J.; Martinez Caicedo, D. A.; Mastbaum, A.; Meddage, V.; Mettler, T.; Miller, K.; Mogan, A.; Mohayai, T.; Moon, J.; Moor, A. F.; Murphy, M.; Naples, D.; Navrer-Agasson, A.; Neely, R. K.; Nienaber, P.; Papadopoulou, A.; Paudel, A.; Pavlovic, Z.; Piasetzky, E.; Porzio, D.; Prince, S.; Qian, X.; Rafique, A.; Reggiani-Guzzo, M.; Ren, L.; Rochester, L.; Ross-Lonergan, M.; Russell, B.; Scanavini, G.; Shaevitz, M. H.; Sinclair, J.; Spentzouris, P.; Stancari, M.; Tang, W.; Terao, K.; Viren, B.; Weber, M.; Williams, Z.; Wolbers, S.; Wospakrik, M.; Wu, W.; Yang, T.; Zhang, C.
Physical review. D, 05/2021, Letnik: 103, Številka: 9Journal Article
We present the multiple particle identification (MPID) network, a convolutional neural network for multiple object classification, developed by MicroBooNE. MPID provides the probabilities that an interaction includes an e−, γ , μ−, π±, and protons in a liquid argon time projection chamber single readout plane. The network extends the single particle identification network previously developed by MicroBooNE Convolutional neural networks applied to neutrino events in a liquid argon time projection chamber, R. Acciarri et al. J. Instrum. 12, P03011 (2017). 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 ν e search analysis. In this paper, we present the network's design, training, and performance on simulation and data from the MicroBooNE detector.
