NuGraph2: A Graph Neural Network for Neutrino Physics Event Reconstruction (2403.11872v1)
Abstract: Liquid Argon Time Projection Chamber (LArTPC) detector technology offers a wealth of high-resolution information on particle interactions, and leveraging that information to its full potential requires sophisticated automated reconstruction techniques. This article describes NuGraph2, a Graph Neural Network (GNN) for low-level reconstruction of simulated neutrino interactions in a LArTPC detector. Simulated neutrino interactions in the MicroBooNE detector geometry are described as heterogeneous graphs, with energy depositions on each detector plane forming nodes on planar subgraphs. The network utilizes a multi-head attention message-passing mechanism to perform background filtering and semantic labelling on these graph nodes, identifying those associated with the primary physics interaction with 98.0\% efficiency and labelling them according to particle type with 94.9\% efficiency. The network operates directly on detector observables across multiple 2D representations, but utilizes a 3D-context-aware mechanism to encourage consistency between these representations. Model inference takes 0.12 s/event on a CPU, and 0.005 s/event batched on a GPU. This architecture is designed to be a general-purpose solution for particle reconstruction in neutrino physics, with the potential for deployment across a broad range of detector technologies, and offers a core convolution engine that can be leveraged for a variety of tasks beyond the two described in this article.
- B. Abi et al. (DUNE), Neutrino interaction classification with a convolutional neural network in the DUNE far detector, Phys. Rev. D 102, 092003 (2020a), arXiv:2006.15052 [physics.ins-det] .
- A. Abed Abud et al. (DUNE), Separation of track- and shower-like energy deposits in ProtoDUNE-SP using a convolutional neural network, Eur. Phys. J. C 82, 903 (2022), arXiv:2203.17053 [physics.ins-det] .
- C. Adams et al. (MicroBooNE), Deep neural network for pixel-level electromagnetic particle identification in the MicroBooNE liquid argon time projection chamber, Phys. Rev. D 99, 092001 (2019), arXiv:1808.07269 [hep-ex] .
- P. Abratenko et al. (MicroBooNE), Convolutional neural network for multiple particle identification in the MicroBooNE liquid argon time projection chamber, Phys. Rev. D 103, 092003 (2021a), arXiv:2010.08653 [hep-ex] .
- C. Choy, J. Gwak, and S. Savarese, 4d spatio-temporal convnets: Minkowski convolutional neural networks, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019) pp. 3075–3084.
- P. Abratenko et al. (MicroBooNE), Semantic segmentation with a sparse convolutional neural network for event reconstruction in MicroBooNE, Phys. Rev. D 103, 052012 (2021b), arXiv:2012.08513 [physics.ins-det] .
- A. Abed Abud (DUNE), Sparse Convolutional Neural Networks for particle classification in ProtoDUNE-SP events, J. Phys. Conf. Ser. 2438, 012125 (2023).
- S. Farrell et al., Novel deep learning methods for track reconstruction, in 4th International Workshop Connecting The Dots 2018 (2018) arXiv:1810.06111 [hep-ex] .
- X. Ju et al. (Exa.TrkX), Performance of a geometric deep learning pipeline for HL-LHC particle tracking, Eur. Phys. J. C 81, 876 (2021), arXiv:2103.06995 [physics.data-an] .
- D. Murnane, S. Thais, and A. Thete, Equivariant Graph Neural Networks for Charged Particle Tracking, in 21th International Workshop on Advanced Computing and Analysis Techniques in Physics Research: AI meets Reality (2023) arXiv:2304.05293 [physics.ins-det] .
- K. Lieret and G. DeZoort, An Object Condensation Pipeline for Charged Particle Tracking at the High Luminosity LHC, in 26th International Conference on Computing in High Energy & Nuclear Physics (2023) arXiv:2309.16754 [physics.data-an] .
- V. Hewes et al. (Exa.TrkX), Graph neural network for object reconstruction in liquid argon time projection chambers, EPJ Web of Conferences 251, 03054 (2021).
- G. Cerati (MicroBooNE), MicroBooNE Public Data Sets: a Collaborative Tool for LArTPC Software Development, in 26th International Conference on Computing in High Energy & Nuclear Physics (2023) arXiv:2309.15362 [hep-ex] .
- R. Acciarri et al. (MicroBooNE), Design and Construction of the MicroBooNE Detector, JINST 12 (02), P02017, arXiv:1612.05824 [physics.ins-det] .
- R. Acciarri et al. (MicroBooNE), The Pandora multi-algorithm approach to automated pattern recognition of cosmic-ray muon and neutrino events in the MicroBooNE detector, Eur. Phys. J. C 78, 82 (2018), arXiv:1708.03135 [hep-ex] .
- https://github.com/vhewes/numl.
- https://github.com/vhewes/pynuml.
- D. Misra, Mish: A self regularized non-monotonic activation function (2020), arXiv:1908.08681 [cs.LG] .
- A. Krizhevsky, I. Sutskever, and G. E. Hinton, Imagenet classification with deep convolutional neural networks, Commun. ACM 60, 84–90 (2017).
- M. Fey and J. E. Lenssen, Fast graph representation learning with pytorch geometric (2019), arXiv:1903.02428 [cs.LG] .
- I. Loshchilov and F. Hutter, Decoupled weight decay regularization (2019), arXiv:1711.05101 [cs.LG] .
- L. N. Smith and N. Topin, Super-convergence: Very fast training of neural networks using large learning rates (2018), arXiv:1708.07120 [cs.LG] .
- A. Kendall, Y. Gal, and R. Cipolla, Multi-task learning using uncertainty to weigh losses for scene geometry and semantics (2018), arXiv:1705.07115 [cs.CV] .
- E. L. Snider and G. Petrillo, LArSoft: Toolkit for Simulation, Reconstruction and Analysis of Liquid Argon TPC Neutrino Detectors, J. Phys. Conf. Ser. 898, 042057 (2017).
- P. Abratenko et al. (MicroBooNE), MicroBooNE BNB Inclusive Overlay Sample (No Wire Info), 10.5281/zenodo.8370883 (2023).
- P. Abratenko et al. (MicroBooNE), MicroBooNE BNB Electron Neutrino Overlay Sample (No Wire Info), 10.5281/zenodo.7261921 (2022).