Antineutron reconstruction in electromagnetic calorimeters with mixed-representation learning
arXiv:2607.11139
The paper introduces a mixed‑representation neural network that combines visual and sequential features to identify antineutrons in electromagnetic calorimeters, enabling direct measurement of both their direction and momentum from ECAL data.
Abstract
A long-standing bottleneck in GeV-scale accelerator experiments lies in reconstructing long-lived neutral hadrons in conventional electromagnetic calorimeters (ECALs), where hadron--nucleus interactions fall outside the detector's native response regime. In this paper, we develop a physics-inspired representation approach for antineutron reconstruction using a large corpus of real collision data. Motivated by two distinct energy deposition patterns from the penetrating high energy antineutrons in ECALs, we propose a Mixed-representation Calorimetric Network (MrCAL) that integrates complementary visual and sequential representation branches within a unified object-detection architecture. This architecture jointly predicts particle identity, momentum direction, and momentum magnitude. Our approach improves the precision of antineutron momentum-direction reconstruction by up to 96% and, for the first time, enables direct measurement of momentum magnitude solely from ECAL readouts, achieving a momentum resolution of approximately 17% at 1 GeV/c. The model maintains robust performance through comprehensive generalization tests spanning a wide variety of physics processes and background environments. This work unlocks a novel measurement capability for legacy ECAL systems at large experimental facilities, broadening their scientific scope via innovative final-state neutral-hadron detection.
29 pages, 11 figures