Interpretable Joint Event-Particle Reconstruction for Neutrino Physics at NOvA with Sparse CNNs and Transformers

• URL: http://arxiv.org/abs/2303.06201v1
• Date: Fri, 10 Mar 2023 20:36:23 GMT
• Title: Interpretable Joint Event-Particle Reconstruction for Neutrino Physics at NOvA with Sparse CNNs and Transformers
• Authors: Alexander Shmakov, Alejandro Yankelevich, Jianming Bian, Pierre Baldi
• Abstract summary: We present a novel neural network architecture that combines the spatial learning enabled by convolutions with the contextual learning enabled by attention. TransformerCVN simultaneously classifies each event and reconstructs every individual particle's identity. This architecture enables us to perform several interpretability studies which provide insights into the network's predictions.
• Score: 124.29621071934693
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The complex events observed at the NOvA long-baseline neutrino oscillation experiment contain vital information for understanding the most elusive particles in the standard model. The NOvA detectors observe interactions of neutrinos from the NuMI beam at Fermilab. Associating the particles produced in these interaction events to their source particles, a process known as reconstruction, is critical for accurately measuring key parameters of the standard model. Events may contain several particles, each producing sparse high-dimensional spatial observations, and current methods are limited to evaluating individual particles. To accurately label these numerous, high-dimensional observations, we present a novel neural network architecture that combines the spatial learning enabled by convolutions with the contextual learning enabled by attention. This joint approach, TransformerCVN, simultaneously classifies each event and reconstructs every individual particle's identity. TransformerCVN classifies events with 90\% accuracy and improves the reconstruction of individual particles by 6\% over baseline methods which lack the integrated architecture of TransformerCVN. In addition, this architecture enables us to perform several interpretability studies which provide insights into the network's predictions and show that TransformerCVN discovers several fundamental principles that stem from the standard model.

Related papers

• NuGraph2: A Graph Neural Network for Neutrino Physics Event Reconstruction [0.3088816319960295]
  This article describes NuGraph2, a Graph Neural Network (GNN) for low-level reconstruction of simulated neutrino interactions in a LArTPC detector. The network operates directly on detector observables across multiple 2D representations, but utilizes a 3D-context-aware mechanism to encourage consistency between these representations.
  arXiv  Detail & Related papers  (2024-03-18T15:26:05Z)
• Deep-learning-based decomposition of overlapping-sparse images: application at the vertex of neutrino interactions [2.5521723486759407]
  This paper presents a solution that leverages the power of deep learning to accurately extract individual objects within multi-dimensional overlapping-sparse images. It is a direct application in high-energy physics with decomposition of overlaid elementary particles obtained from imaging detectors.
  arXiv  Detail & Related papers  (2023-10-30T16:12:25Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• Transformer with Implicit Edges for Particle-based Physics Simulation [135.77656965678196]
  Transformer with Implicit Edges (TIE) captures the rich semantics of particle interactions in an edge-free manner. We evaluate our model on diverse domains of varying complexity and materials.
  arXiv  Detail & Related papers  (2022-07-22T03:45:29Z)
• Trapped-Ion Quantum Simulation of Collective Neutrino Oscillations [55.41644538483948]
  We study strategies to simulate the coherent collective oscillations of a system of N neutrinos in the two-flavor approximation using quantum computation. We find that the gate complexity using second order Trotter- Suzuki formulae scales better with system size than with other decomposition methods such as Quantum Signal Processing.
  arXiv  Detail & Related papers  (2022-07-07T09:39:40Z)
• Quench dynamics of R\'enyi negativities and the quasiparticle picture [0.0]
  We study the time evolution after a quantum quench of the moments of the partial transpose. We show that, in the space-time scaling limit of long times and large subsystems, a quasiparticle description allows for a complete understanding of the R'enyi negativities.
  arXiv  Detail & Related papers  (2021-10-27T17:07:25Z)
• Spectral density reconstruction with Chebyshev polynomials [77.34726150561087]
  We show how to perform controllable reconstructions of a finite energy resolution with rigorous error estimates. This paves the way for future applications in nuclear and condensed matter physics.
  arXiv  Detail & Related papers  (2021-10-05T15:16:13Z)
• Scalable, End-to-End, Deep-Learning-Based Data Reconstruction Chain for Particle Imaging Detectors [0.0]
  This paper introduces an end-to-end, ML-based data reconstruction chain for Liquid Time Projection Chambers (LArTPCs) It is the first implementation to handle the unprecedented pile-up of dozens of high energy neutrino interactions.
  arXiv  Detail & Related papers  (2021-02-01T18:10:00Z)
• Graph Neural Network for Hamiltonian-Based Material Property Prediction [56.94118357003096]
  We present and compare several different graph convolution networks that are able to predict the band gap for inorganic materials. The models are developed to incorporate two different features: the information of each orbital itself and the interaction between each other. The results show that our model can get a promising prediction accuracy with cross-validation.
  arXiv  Detail & Related papers  (2020-05-27T13:32:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.