Speaker
Description
The LHCf experiment aims to study forward neutral particle production at the LHC, providing crucial data for improving hadronic interaction models used in cosmic ray physics. A key challenge in this context is the
measurement of $(K^0)$ production, indirectly reconstructed from the four photons originated by its decay. The main challenge in this measurement is the reconstruction of events with multiple calorimetric hits.
To address this, we developed a machine learning pipeline that employs multiple neural networks to classify and reconstruct such events. The pipeline consists of four stages: (1) event identification, determining whether an event contains four particles, (2) photon/neutron discrimination for each particle hit, (3) event tagging into four specific topologies based on the distribution of photons between the two calorimeter towers, and (4) position and energy regression for each detected photon.
The model takes as input the energy deposits in each channel of the Arm2 detector, composed by two calorimetric towers with 16 GSO scintillator per tower and 4 pairs of silicon microstrip detectors oriented along the x and y axes, placed at different depths in the calorimeter. The network architecture is designed to process these heterogeneous data sources, allowing for a precise reconstruction of the event topology. Preliminary results, obtained with a dataset of 10k simulated events, show that the classification networks reach over 80\% accuracy in selecting relevant events and distinguishing photon/neutron interactions. These promising results highlight the potential of deep learning techniques in enhancing event reconstruction at LHCf and lay the groundwork for further improvements with larger datasets and refined models.
Significance
This presentation introduces a novel machine learning pipeline specifically developed for the reconstruction of K0 events in the LHCf experiment. Unlike previous approaches that relied on traditional reconstruction methods, our work leverages multiple deep neural networks to handle complex multi-particle calorimetric events. The pipeline is designed to identify event topologies, discriminate between photon and neutron interactions, and accurately reconstruct particle positions and energies. Preliminary results show significant improvement in classification accuracy, exceeding 80%, even at this early stage with a limited simulation dataset. These developments represent a meaningful step forward in event reconstruction at LHCf and are expected to enhance the experiment's ability to constrain hadronic interaction models, with direct impact on cosmic ray physics.
| Experiment context, if any | LHCf |
|---|
