Purpose The Jiangmen Underground Neutrino Observatory(JUNO)is designed to determine the neutrino mass ordering and measure neutrino oscillation parameters.A precise muon reconstruction is crucial to reduce one of the ...Purpose The Jiangmen Underground Neutrino Observatory(JUNO)is designed to determine the neutrino mass ordering and measure neutrino oscillation parameters.A precise muon reconstruction is crucial to reduce one of the major backgrounds induced by cosmic muons.Methods This article proposes a novel muon reconstruction method based on convolutional neural network(CNN)models.In this method,the track information reconstructed by the top tracker is used for network training.The training dataset is augmented by applying a rotation to muon tracks to compensate for the limited angular coverage of the top tracker.Result The muon reconstruction with the CNN model can produce unbiased tracks with performance that spatial resolution is better than 10 cm and angular resolution is better than 0.6◦.By using a GPU-accelerated implementation,a speedup factor of 100 compared to existing CPU techniques has been demonstrated.展开更多
基金Supported by Strategic Priority Research Program of Chinese Academy of Sciences(XDA10010900)NSFC(11805223).
文摘Purpose The Jiangmen Underground Neutrino Observatory(JUNO)is designed to determine the neutrino mass ordering and measure neutrino oscillation parameters.A precise muon reconstruction is crucial to reduce one of the major backgrounds induced by cosmic muons.Methods This article proposes a novel muon reconstruction method based on convolutional neural network(CNN)models.In this method,the track information reconstructed by the top tracker is used for network training.The training dataset is augmented by applying a rotation to muon tracks to compensate for the limited angular coverage of the top tracker.Result The muon reconstruction with the CNN model can produce unbiased tracks with performance that spatial resolution is better than 10 cm and angular resolution is better than 0.6◦.By using a GPU-accelerated implementation,a speedup factor of 100 compared to existing CPU techniques has been demonstrated.
