The Pandora Software Development Kit for Pattern Recognition

Abstract

The development of automated solutions to pattern recognition problems is important in many areas of scientific research and human endeavour. This paper describes the implementation of the Pandora Software Development Kit, which aids the process of designing, implementing and running pattern recognition algorithms. The Pandora Application Programming Interfaces ensure simple specification of the building-blocks defining a pattern recognition problem. The logic required to solve the problem is implemented in algorithms. The algorithms request operations to create or modify data structures and the operations are performed by the Pandora framework. This design promotes an approach using many decoupled algorithms, each addressing specific topologies. Details of algorithms addressing two pattern recognition problems in High Energy Physics are presented: reconstruction of events at a high-energy e+e- linear collider and reconstruction of cosmic ray or neutrino events in a liquid argon time projection chamber.

Accepted by European Physical Journal C, 4 September 2015

References in corpus (1)

• PYTHIA 6.4 Physics and Manual

Cited by in corpus (43)

• Higgs Physics at the CLIC Electron-Positron Linear Collider
• First results on ProtoDUNE-SP liquid argon time projection chamber performance from a beam test at the CERN Neutrino Platform
• Top-Quark Physics at the CLIC Electron-Positron Linear Collider
• MeV-scale sterile neutrino decays at the Fermilab Short-Baseline Neutrino program
• Jet reconstruction at high-energy lepton colliders
• Determination of muon momentum in the MicroBooNE LArTPC using an improved model of multiple Coulomb scattering
• Search for heavy neutral leptons decaying into muon-pion pairs in the MicroBooNE detector
• Double Higgs boson production and Higgs self-coupling extraction at CLIC
• Calomplification -- The Power of Generative Calorimeter Models
• Neutrino interaction classification with a convolutional neural network in the DUNE far detector
• Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph and image data
• A Convolutional Neural Network for Multiple Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
• Software compensation in Particle Flow reconstruction
• Search for long-lived heavy neutral leptons and Higgs portal scalars decaying in the MicroBooNE detector
• Mono-chromatic single photon events at the muon collider
• Measurement of cosmic-ray reconstruction efficiencies in the MicroBooNE LArTPC using a small external cosmic-ray counter
• Comparison of νμ-Ar multiplicity distributions observed by MicroBooNE to GENIE model predictions
• The science and technology of liquid argon detectors
• Separation of track- and shower-like energy deposits in ProtoDUNE-SP using a convolutional neural network
• Long-baseline neutrino oscillation physics potential of the DUNE experiment
• Optimising longitudinal and lateral calorimeter granularity for software compensation in hadronic showers using deep neural networks
• Probing gauge-Higgs Unification models at the ILC with quark-antiquark forward-backward asymmetry at center-of-mass energies above the Z mass
• Improved particle-flow event reconstruction with scalable neural networks for current and future particle detectors
• Point Proposal Network for Reconstructing 3D Particle Endpoints with Sub-Pixel Precision in Liquid Argon Time Projection Chambers
• First Measurement of the Total Inelastic Cross-Section of Positively-Charged Kaons on Argon at Energies Between 5.0 and 7.5 GeV
• Accelerating Machine Learning Inference with GPUs in ProtoDUNE Data Processing
• Kinematic Edge Detection Using Finite Impulse Response Filters
• Operation of the Trigger System for the ICARUS Detector at Fermilab
• Updating the SiD Detector concept
• Tau lepton identification and reconstruction: a new frontier for jet-tagging ML algorithms
• A unified machine learning approach for reconstructing hadronically decaying tau leptons
• Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders
• Pair-production of the charged IDM scalars at high energy CLIC
• Measurement of single charged pion production in charged-current ${\nu }_{\mu }$-Ar interactions with the MicroBooNE detector
• Optimization of timing selections at 380 GeV CLIC
• CaloHadronic: a diffusion model for the generation of hadronic showers
• Physics potential for boosted topologies in top-quark pair production at a multi-TeV Compact Linear Collider
• All-hadronic HHZ production at 3 TeV CLIC
• Neutrino Interaction Vertex Reconstruction in DUNE with Pandora Deep Learning
• Searching for solar KDAR with DUNE
• The potential of discrimination methods in a high pressure xenon TPC for the search of the neutrinoless double-beta decay of Xe-136
• APRIL : a novel Algorithm for Particle Reconstruction at ILC
• LArTPC hit-based topology classification with quantum machine learning and symmetry