Optimal Transport for e/π⁰ Particle Classification in LArTPC Neutrino Experiments

2025/06/10 by Caratelli, David, Craig, Nathaniel, Fang, Chuyue +1
#FOS: Physical sciences #High Energy Physics - Experiment (hep-ex) #High Energy Physics - Phenomenology (hep-ph) #Instrumentation and Detectors (physics.ins-det)

paper · doi:10.48550/arxiv.2506.09238

Abstract

The efficient classification of electromagnetic activity from π⁰ and electrons remains an open problem in the reconstruction of neutrino interactions in Liquid Argon Time Projection Chamber (LArTPC) detectors. We address this problem using the mathematical framework of Optimal Transport (OT), which has been successfully employed for event classification in other HEP contexts and is ideally suited to the high-resolution calorimetry of LArTPCs. Using a publicly available simulated dataset from the MicroBooNE collaboration, we show that OT methods achieve state-of-the-art reconstruction performance in e/π⁰ classification. The success of this first application indicates the broader promise of OT methods for LArTPC-based neutrino experiments.

Citations

• Operation of a Modular 3D-Pixelated Liquid Argon Time-Projection Chamber in a Neutrino Beam
• A continuous calibration of the ATLAS flavour-tagging classifiers via optimal transportation maps
• From oversimplified to overlooked: the case for exploring Rich Dark Sectors
• Factorization for Collider Dataspace Correlators
• First measurement of ν_e + ν_e charged current single charged pion production differential cross sections on argon using the MicroBooNE detector
• Non-Gaussianities in Collider Metric Binning
• First Search for Dark Sector e⁺e^- Explanations of the MiniBooNE Anomaly at MicroBooNE
• Enhancing anomaly detection with topology-aware autoencoders
• First Search for Neutral Current Coherent Single-Photon Production in MicroBooNE
• Inclusive Search for Anomalous Single-Photon Production in MicroBooNE
• Multi-scale Optimal Transport for Complete Collider Events
• Search for an Anomalous Production of Charged-Current ν_e Interactions Without Visible Pions Across Multiple Kinematic Observables in MicroBooNE
• SPECTER: Efficient Evaluation of the Spectral EMD
• A Field Guide to Event-Shape Observables Using Optimal Transport
• Accelerating template generation in resonant anomaly detection searches with optimal transport
• Improving neutrino energy estimation of charged-current interaction events with recurrent neural networks in MicroBooNE
• Graph Neural Network for Neutrino Physics Event Reconstruction
• Performance of a modular ton-scale pixel-readout liquid argon time projection chamber
• Exploring Optimal Transport for Event-Level Anomaly Detection at the Large Hadron Collider
• First search for dark-trident processes using the MicroBooNE detector
• Unsupervised learning in the metric space of jets
• The DUNE Far Detector Vertical Drift Technology, Technical Design Report
• Decorrelation using Optimal Transport
• A Spectral Metric for Collider Geometry
• ICARUS at the Fermilab Short-Baseline Neutrino Program -- Initial Operation
• Snowmass Neutrino Frontier Report
• Background Modeling for Double Higgs Boson Production: Density Ratios and Optimal Transport
• Dark Sector Studies with Neutrino Beams
• Towards Designing and Exploiting Generative Networks for Neutrino Physics Experiments using Liquid Argon Time Projection Chambers
• Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance
• Search for an anomalous excess of charged-current ν_e interactions without pions in the final state with the MicroBooNE experiment
• An Exploration of Learnt Representations of W Jets
• A Living Review of Machine Learning for Particle Physics
• Scalable, End-to-End, Deep-Learning-Based Data Reconstruction Chain for Particle Imaging Detectors
• Clustering of Electromagnetic Showers and Particle Interactions with Graph Neural Networks in Liquid Argon Time Projection Chambers Data
• A Robust Measure of Event Isotropy at Colliders
• Deep Underground Neutrino Experiment (DUNE), Far Detector Technical Design Report, Volume I: Introduction to DUNE
• Sample Complexity of Sinkhorn divergences
• Deep neural network for pixel-level electromagnetic particle identification in the MicroBooNE liquid argon time projection chamber
• Hyper-Kamiokande Design Report
• The Pandora multi-algorithm approach to automated pattern recognition of cosmic-ray muon and neutrino events in the MicroBooNE detector
• MicroBooNE
• Nearest neighbor pattern classification

Related

• Enhanced Reconstruction of Sub-GeV Neutrinos Charged Current Interactions in LArTPC
• Electron Neutrino Classification in Liquid Argon Time Projection Chamber\n Detector
• Energy Reconstruction and Calibration of the MicroBooNE LArTPC
• Exclusive Topologies reconstruction in LAr-TPC experiments: a Novel Approach for precise Neutrino-Nucleus Cross-Sections Measurements
• Physics Prospects with MeV Neutrino-Argon Charged Current Interactions using Enhanced Photon Detection in Future LArTPCs