The Large High Altitude Air Shower Observatory(LHAASO)(Fig.1)is located at Mt.Haizi(4410 m a.s.l.,600 g/cm^(2),29°21'27.56"N,100°08'19.66"E)in Daocheng,Sichuan province,P.R.China.LHAASO con...The Large High Altitude Air Shower Observatory(LHAASO)(Fig.1)is located at Mt.Haizi(4410 m a.s.l.,600 g/cm^(2),29°21'27.56"N,100°08'19.66"E)in Daocheng,Sichuan province,P.R.China.LHAASO consists of 1.3 km^(2) array(KM2A)of electromagnetic particle detectors(ED)and muon detectors(MD),a water Cherenkov detector array(WCDA)with a total active area of 78,000 m^(2),18 wide field-of-view air Cherenkov telescopes(WFCTA)and a newly proposed electron-neutron detector array(ENDA)covering 10,000 m^(2).Each detector is synchronized with all the other through a clock synchronization network based on the White Rabbit protocol.The observatory includes an IT center which comprises the data acquisition system and trigger system,the data analysis facility.In this Chapter,all the above-mentioned components of LHAASO as well as infrastructure are described.展开更多
The precise measurement of cosmic-ray(CR) knees of different primaries is essential to reveal CR acceleration and propagation mechanisms, as well as to explore new physics. However, the classification of CR components...The precise measurement of cosmic-ray(CR) knees of different primaries is essential to reveal CR acceleration and propagation mechanisms, as well as to explore new physics. However, the classification of CR components is a difficult task, especially for groups with similar atomic numbers. Given that deep learning achieved remarkable breakthroughs in numerous fields, we seek to leverage this technology to improve the classification performance of the CR Proton and Light groups in the LHAASO-KM2A experiment. In this study, we propose a fused graph neural network model for KM2A arrays, where the activated detectors are structured into graphs. We find that the signal and background are effectively discriminated in this model, and its performance outperforms both the traditional physicsbased method and the convolutional neural network(CNN)-based model across the entire energy range.展开更多
基金Supported by National Natural Science Foundation in China(NSFC)(U2031103,U1831208,11805209,11775233)NSFC for Distinguished Young Scholars(12025502)+1 种基金the Science and Technology Department of Sichuan Province(2021YFSY0031)the International Partnership Program of Chinese Academy of Sciences(113111KYSB20170055)。
文摘The Large High Altitude Air Shower Observatory(LHAASO)(Fig.1)is located at Mt.Haizi(4410 m a.s.l.,600 g/cm^(2),29°21'27.56"N,100°08'19.66"E)in Daocheng,Sichuan province,P.R.China.LHAASO consists of 1.3 km^(2) array(KM2A)of electromagnetic particle detectors(ED)and muon detectors(MD),a water Cherenkov detector array(WCDA)with a total active area of 78,000 m^(2),18 wide field-of-view air Cherenkov telescopes(WFCTA)and a newly proposed electron-neutron detector array(ENDA)covering 10,000 m^(2).Each detector is synchronized with all the other through a clock synchronization network based on the White Rabbit protocol.The observatory includes an IT center which comprises the data acquisition system and trigger system,the data analysis facility.In this Chapter,all the above-mentioned components of LHAASO as well as infrastructure are described.
基金Supported by the National Key R&D Program of China(2018YFA0404201)the Natural Sciences Foundation of China(11575203,11635011)。
文摘The precise measurement of cosmic-ray(CR) knees of different primaries is essential to reveal CR acceleration and propagation mechanisms, as well as to explore new physics. However, the classification of CR components is a difficult task, especially for groups with similar atomic numbers. Given that deep learning achieved remarkable breakthroughs in numerous fields, we seek to leverage this technology to improve the classification performance of the CR Proton and Light groups in the LHAASO-KM2A experiment. In this study, we propose a fused graph neural network model for KM2A arrays, where the activated detectors are structured into graphs. We find that the signal and background are effectively discriminated in this model, and its performance outperforms both the traditional physicsbased method and the convolutional neural network(CNN)-based model across the entire energy range.
