Semantic Segmentation with a Sparse Convolutional Neural Network for Event Reconstruction in MicroBooNE

Abstract

We present the performance of a semantic segmentation network, SparseSSNet, that provides pixel-level classification of MicroBooNE data. The MicroBooNE experiment employs a liquid argon time projection chamber for the study of neutrino properties and interactions. SparseSSNet is a submanifold sparse convolutional neural network, which provides the initial machine learning based algorithm utilized in one of MicroBooNE's ${\nu }_e$-appearance oscillation analyses. The network is trained to categorize pixels into five classes, which are re-classified into two classes more relevant to the current analysis. The output of SparseSSNet is a key input in further analysis steps. This technique, used for the first time in liquid argon time projection chambers data and is an improvement compared to a previously used convolutional neural network, both in accuracy and computing resource utilization. The accuracy achieved on the test sample is $\ge 99\%$. For full neutrino interaction simulations, the time for processing one image is $\approx$ 0.5 sec, the memory usage is at 1 GB level, which allows utilization of most typical CPU worker machine.

References in corpus (22)

• Machine learning and the physical sciences
• Significant Excess of ElectronLike Events in the MiniBooNE Short-Baseline Neutrino Experiment
• Submanifold Sparse Convolutional Networks
• The Neutrino Flux prediction at MiniBooNE
• A Proposal for a Three Detector Short-Baseline Neutrino Oscillation Program in the Fermilab Booster Neutrino Beam
• A Convolutional Neural Network Neutrino Event Classifier
• Ionization Electron Signal Processing in Single Phase LArTPCs II. Data/Simulation Comparison and Performance in MicroBooNE
• Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber
• Noise Characterization and Filtering in the MicroBooNE Liquid Argon TPC
• Ionization Electron Signal Processing in Single Phase LArTPCs I. Algorithm Description and Quantitative Evaluation with MicroBooNE Simulation
• A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
• First Measurement of Inclusive Muon Neutrino Charged Current Differential Cross Sections on Argon at $E_{\nu }\sim 0.8$ GeV with the MicroBooNE Detector
• Long-Baseline Neutrino Facility (LBNF) and Deep Underground Neutrino Experiment (DUNE) Conceptual Design Report, Volume 4 The DUNE Detectors at LBNF
• Measurement of Space Charge Effects in the MicroBooNE LArTPC Using Cosmic Muons
• The GENIE Neutrino Monte Carlo Generator: Physics and User Manual
• Deep Neural Networks for Energy and Position Reconstruction in EXO-200
• Scalable Deep Convolutional Neural Networks for Sparse, Locally Dense Liquid Argon Time Projection Chamber Data
• Reconstruction and Measurement of $\mathcal{O}$(100) MeV Energy Electromagnetic Activity from ${\pi }^0\to \gamma \gamma$ Decays in the MicroBooNE LArTPC
• Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment
• Vertex-Finding and Reconstruction of Contained Two-track Neutrino Events in the MicroBooNE Detector
• Enhancing Neutrino Event Reconstruction with Pixel-Based 3D Readout for Liquid Argon Time Projection Chambers
• Scalable, Proposal-free Instance Segmentation Network for 3D Pixel Clustering and Particle Trajectory Reconstruction in Liquid Argon Time Projection Chambers

Cited by in corpus (17)

• Heavy neutral leptons below the kaon mass at hodoscopic detectors
• Search for an anomalous excess of charged-current quasi-elastic ${\nu }_e$ interactions with the MicroBooNE experiment using Deep-Learning-based reconstruction
• A Convolutional Neural Network for Multiple Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
• Wire-Cell 3D Pattern Recognition Techniques for Neutrino Event Reconstruction in Large LArTPCs: Algorithm Description and Quantitative Evaluation with MicroBooNE Simulation
• Pulse shape discrimination using a convolutional neural network for organic liquid scintillator signals
• Convolutional Neural Networks for Shower Energy Prediction in Liquid Argon Time Projection Chambers
• Neural Network predictions of inclusive electron-nucleus cross sections
• Self-compensating Light Calorimetry with Liquid Argon Time Projection Chamber for GeV Neutrino Physics
• Domain-informed neural networks for interaction localization within astroparticle experiments
• Graph Neural Network for Neutrino Physics Event Reconstruction
• Artificial intelligence for improved fitting of trajectories of elementary particles in inhomogeneous dense materials immersed in a magnetic field
• Transforming a rare event search into a not-so-rare event search in real-time with deep learning-based object detection
• Implications of MicroBooNE's low sensitivity to electron antineutrino interactions in the search for the MiniBooNE excess
• TrackFormers: In Search of Transformer-Based Particle Tracking for the High-Luminosity LHC Era
• Contrastive Learning for Robust Representations of Neutrino Data
• LArTPC hit-based topology classification with quantum machine learning and symmetry
• Refine Neutrino Events Reconstruction with BEiT-3