期刊
PHYSICAL REVIEW D
卷 99, 期 1, 页码 -出版社
AMER PHYSICAL SOC
DOI: 10.1103/PhysRevD.99.012011
关键词
-
资金
- U.S. Department of Energy
- U.S. National Science Foundation
- University of California, Irvine
- Department of Science and Technology, India
- European Research Council
- MSMT CR, Czech Republic
- RAS, Russian Ministry of Education and Science (RMES), Russia
- RFBR, Russia
- CNPq, Brazil
- FAPEG, Brazil
- State of Minnesota
- University of Minnesota
- U.S. DOE [De-AC02-07CH11359]
- DOE [DE-FOA-0001781]
In neutrino experiments, neutrino energy reconstruction is crucial because neutrino oscillations and differential cross-sections are functions of neutrino energy. It is also challenging due to the complexity in the detector response and kinematics of final state particles. We propose a regression convolutional neural network (CNN) based method to reconstruct electron neutrino energy and electron energy in the NOvA neutrino experiment. We demonstrate that with raw detector pixel inputs, a regression CNN can reconstruct event energy even with complicated final states involving lepton and hadrons. Compared with kinematics-based energy reconstruction, this method achieves a significantly better energy resolution. The reconstructed to true energy ratio shows comparable or less dependence on true energy, hadronic energy fractions, and interaction modes. The regression CNN also shows smaller systematic uncertainties from the simulation of neutrino interactions. The proposed energy estimator provides improvements of 16% and 12% in RMS for nu(e) CC and electron, respectively. This method can also be extended to solve other regression problems in High Energy Physics, taking over kinematics-based reconstruction tasks.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据