使用Smask-RCNN的微体液体氩时间投影室的宇宙射线MUON聚类

论文标题

使用Smask-RCNN的微体液体氩时间投影室的宇宙射线MUON聚类

Cosmic ray muon clustering for the MicroBooNE liquid argon time projection chamber using sMask-RCNN

论文作者

MicroBooNE collaboration, Abratenko, P., An, R., Anthony, J., Arellano, L., Asaadi, J., Ashkenazi, A., Balasubramanian, S., Baller, B., Barnes, C., Barr, G., Barrow, J., Basque, V., Bathe-Peters, L., Rodrigues, O. Benevides, Berkman, S., Bhanderi, A., Bhat, A., Bishai, M., Blake, A., Bolton, T., Book, J. Y., Camilleri, L., Caratelli, D., Terrazas, I. Caro, Cavanna, F., Cerati, G., Chen, Y., Church, E., Cianci, D., Conrad, J. M., Convery, M., Cooper-Troendle, L., Crespo-Anadon, J. I., Del Tutto, M., Dennis, S. R., Detje, P., Devitt, A., Diurba, R., Dorrill, R., Duffy, K., Dytman, S., Eberly, B., Ereditato, A., Evans, J. J., Fine, R., Aguirre, G. A. Fiorentini, Fitzpatrick, R. S., Fleming, B. T., Foppiani, N., Franco, D., Furmanski, A. P., Garcia-Gamez, D., Gardiner, S., Ge, G., Gollapinni, S., Goodwin, O., Gramellini, E., Green, P., Greenlee, H., Gu, W., Guenette, R., Guzowski, P., Hagaman, L., Hen, O., Hilgenberg, C., Horton-Smith, G. A., Hourlier, A., Itay, R., James, C., Ji, X., Jiang, L., Jo, J. H., Johnson, R. A., Jwa, Y. J., Kalra, D., Kamp, N., Kaneshige, N., Karagiorgi, G., Ketchum, W., Kirby, M., Kobilarcik, T., Kreslo, I., Lepetic, I., Li, J. -Y., Li, K., Li, Y., Lin, K., Littlejohn, B. R., Louis, W. C., Luo, X., Manivannan, K., Mariani, C., Marsden, D., Marshall, J., Caicedo, D. A. Martinez, Mason, K., Mastbaum, A., McConkey, N., Meddage, V., Mettler, T., Miller, K., Mills, J., Mistry, K., Mohayai, T., Mogan, A., Moon, J., Mooney, M., Moor, A. F., Moore, C. D., Lepin, L. Mora, Mousseau, J., Babu, S. Mulleria, Murphy, M., Naples, D., Navrer-Agasson, A., Nebot-Guinot, M., Neely, R. K., Newmark, D. A., Nowak, J., Nunes, M., Palamara, O., Paolone, V., Papadopoulou, A., Papavassiliou, V., Pate, S. F., Patel, N., Paudel, A., Pavlovic, Z., Piasetzky, E., Ponce-Pinto, I., Prince, S., Qian, X., Raaf, J. L., Radeka, V., Rafique, A., Reggiani-Guzzo, M., Ren, L., Rice, L. C. J., Rochester, L., Rondon, J. Rodriguez, Rosenberg, M., Ross-Lonergan, M., Scanavini, G., Schmitz, D. W., Schukraft, A., Seligman, W., Shaevitz, M. H., Sharankova, R., Shi, J., Sinclair, J., Smith, A., Snider, E. L., Soderberg, M., Soldner-Rembold, S., Spentzouris, P., Spitz, J., Stancari, M., John, J. St., Strauss, T., Sutton, K., Sword-Fehlberg, S., Szelc, A. M., Tang, W., Terao, K., Thorpe, C., Totani, D., Toups, M., Tsai, Y. -T., Uchida, M. A., Usher, T., Van De Pontseele, W., Viren, B., Weber, M., Wei, H., Williams, Z., Wolbers, S., Wongjirad, T., Wospakrik, M., Wresilo, K., Wright, N., Wu, W., Yandel, E., Yang, T., Yarbrough, G., Yates, L. E., Yu, F. J., Yu, H. W., Zeller, G. P., Zennamo, J., Zhang, C.

论文摘要

在本文中，我们描述了基于掩模区域的卷积神经网络（Mask-RCNN）的修改实现，用于液体氩TPC中的宇宙射线MUON聚类，并应用于Microboone Neutrino数据。我们对该网络的实现（称为Smask-RCNN）使用稀疏的Submanifold汇总来提高稀疏数据集上的处理速度，并将其与几个指标的原始密集版本进行了比较。对网络进行了训练，可以使用来自微生物液体氩时间投影室的电线读数图像作为输入，并在图像中产生单独标记的粒子相互作用。这些输出被识别为宇宙射线muon或电子中微子相互作用。我们发现，Smask-RCNN的平均像素聚类效率为85.9％，而密集网络的平均像素聚类效率为89.1％。我们证明了Smask-Rcnn与Microboone的最先进的电线宇宙标记器结合使用的能力，以否决否包含宇宙射线MUON的否决权。在同一电子中微子事件信号效率下，将Smask-RCNN添加到线细胞宇宙标记处删除了70％的剩余宇宙射线MUON背景事件。该事件否决权可以提供唯一的宇宙射线背景事件的99.7％的拒绝，同时保持电子中微子事件级信号效率为80.1％。除了宇宙光线识别外，SMASK-RCNN还可用于提取特征并识别其他3D跟踪检测器中的不同粒子相互作用类型。

In this article, we describe a modified implementation of Mask Region-based Convolutional Neural Networks (Mask-RCNN) for cosmic ray muon clustering in a liquid argon TPC and applied to MicroBooNE neutrino data. Our implementation of this network, called sMask-RCNN, uses sparse submanifold convolutions to increase processing speed on sparse datasets, and is compared to the original dense version in several metrics. The networks are trained to use wire readout images from the MicroBooNE liquid argon time projection chamber as input and produce individually labeled particle interactions within the image. These outputs are identified as either cosmic ray muon or electron neutrino interactions. We find that sMask-RCNN has an average pixel clustering efficiency of 85.9% compared to the dense network's average pixel clustering efficiency of 89.1%. We demonstrate the ability of sMask-RCNN used in conjunction with MicroBooNE's state-of-the-art Wire-Cell cosmic tagger to veto events containing only cosmic ray muons. The addition of sMask-RCNN to the Wire-Cell cosmic tagger removes 70% of the remaining cosmic ray muon background events at the same electron neutrino event signal efficiency. This event veto can provide 99.7% rejection of cosmic ray-only background events while maintaining an electron neutrino event-level signal efficiency of 80.1%. In addition to cosmic ray muon identification, sMask-RCNN could be used to extract features and identify different particle interaction types in other 3D-tracking detectors.

下载PDF全文

下载文献需遵守相关版权规定

论文标题