Speaker
Description
In previous work, a deep neural network was shown to improve the reconstruction of inclusive kinematic variables in neutral-current deep inelastic scattering. Building on this approach, we present a particle flow network (PFN) for reconstructing semi-inclusive kinematic variables. The PFN takes as input the kinematics of the scattered electron, the hadronic final state, and the inclusive kinematic variables. We evaluate our network using simulated events for the ePIC detector at the future Electron-Ion Collider (EIC) and compare its performance with existing reconstruction methods. We find that the PFN provides improved reconstruction of semi-inclusive kinematic variables, including events with initial- and final-state radiation. This improvement reduces the systematic uncertainties in semi-inclusive measurements and enhances the precision of future nucleon structure studies at the EIC.