Speaker
Description
The measurement of the energy spectrum of high-energy cosmic ray particles is crucial for understanding extreme astrophysical processes and the origins of cosmic rays. It is also one of the core scientific objectives of the LHAASO-KM2A experiment. Traditional energy reconstruction methods, such as maximum likelihood estimation and parametric fitting, rely on simplified assumptions about the lateral distribution of air showers and face significant systematic errors due to enhanced shower fluctuations and the nonlinear effects of detector response. To overcome this challenge, this study proposes an energy reconstruction methods based on a Graph Neural Network (GNN). Experiments show that, based on simulated data, the GNN offers a significant improvement in energy resolution in the knee region energy interval compared to traditional parametric methods.
| Collaboration(s) | LHAASO Collaboration |
|---|
