NuBench: An Open Benchmark for Deep Learning-Based Event Reconstruction in Neutrino Telescopes

• URL: http://arxiv.org/abs/2511.13111v2
• Date: Wed, 19 Nov 2025 08:23:15 GMT
• Title: NuBench: An Open Benchmark for Deep Learning-Based Event Reconstruction in Neutrino Telescopes
• Authors: Rasmus F. Orsoe, Stephan Meighen-Berger, Jeffrey Lazar, Jorge Prado, Ivan Mozun-Mateo, Aske Rosted, Philip Weigel, Arturo Llorente Anaya,
• Abstract summary: We present NuBench, an open benchmark for deep learning-based event reconstruction in neutrino telescopes.<n>NuBench comprises seven large-scale simulated datasets containing nearly 130 million charged- and neutral-current muon-neutrino interactions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neutrino telescopes are large-scale detectors designed to observe Cherenkov radiation produced from neutrino interactions in water or ice. They exist to identify extraterrestrial neutrino sources and to probe fundamental questions pertaining to the elusive neutrino itself. A central challenge common across neutrino telescopes is to solve a series of inverse problems known as event reconstruction, which seeks to resolve properties of the incident neutrino, based on the detected Cherenkov light. In recent times, significant efforts have been made in adapting advances from deep learning research to event reconstruction, as such techniques provide several benefits over traditional methods. While a large degree of similarity in reconstruction needs and low-level data exists, cross-experimental collaboration has been hindered by a lack of diverse open-source datasets for comparing methods. We present NuBench, an open benchmark for deep learning-based event reconstruction in neutrino telescopes. NuBench comprises seven large-scale simulated datasets containing nearly 130 million charged- and neutral-current muon-neutrino interactions spanning 10 GeV to 100 TeV, generated across six detector geometries inspired by existing and proposed experiments. These datasets provide pulse- and event-level information suitable for developing and comparing machine-learning reconstruction methods in both water and ice environments. Using NuBench, we evaluate four reconstruction algorithms - ParticleNeT and DynEdge, both actively used within the KM3NeT and IceCube collaborations, respectively, along with GRIT and DeepIce - on up to five core tasks: energy and direction reconstruction, topology classification, interaction vertex prediction, and inelasticity estimation.

Related papers

• Fast and Reliable Probabilistic Reflectometry Inversion with Prior-Amortized Neural Posterior Estimation [73.81105275628751]
  Finding all structures compatible with reflectometry data is computationally prohibitive for standard algorithms. We address this lack of reliability with a probabilistic deep learning method that identifies all realistic structures in seconds. Our method, Prior-Amortized Neural Posterior Estimation (PANPE), combines simulation-based inference with novel adaptive priors.
  arXiv  Detail & Related papers  (2024-07-26T10:29:16Z)
• Neutrino Reconstruction in TRIDENT Based on Graph Neural Network [6.301679261460378]
  TRopIcal DEep-sea Neutrino Telescope (TRIDENT) is a next-generation neutrino telescope to be located in the South China Sea.
  arXiv  Detail & Related papers  (2024-01-27T06:57:24Z)
• 2D Convolutional Neural Network for Event Reconstruction in IceCube DeepCore [0.0]
  IceCube DeepCore is an extension of the IceCube Neutrino Observatory designed to measure GeV scale atmospheric neutrino interactions. Distinguishing muon neutrinos from other flavors and reconstructing inelasticity are especially difficult tasks at GeV scale energies. We present a new CNN model that exploits time and depth translational symmetry in IceCube DeepCore data.
  arXiv  Detail & Related papers  (2023-07-31T02:37:36Z)
• Interpretable Joint Event-Particle Reconstruction for Neutrino Physics at NOvA with Sparse CNNs and Transformers [124.29621071934693]
  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.
  arXiv  Detail & Related papers  (2023-03-10T20:36:23Z)
• 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)
• Geo-NI: Geometry-aware Neural Interpolation for Light Field Rendering [58.30139863914237]
  We present a Geometry-aware Neural Interpolation (Geo-NI) framework for light field rendering.<n>By combining the superiorities of NI and DIBR, the proposed Geo-NI is able to render views with large disparity.
  arXiv  Detail & Related papers  (2022-06-20T12:25:34Z)
• 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)
• Simulation of Collective Neutrino Oscillations on a Quantum Computer [117.44028458220427]
  We present the first simulation of a small system of interacting neutrinos using current generation quantum devices. We introduce a strategy to overcome limitations in the natural connectivity of the qubits and use it to track the evolution of entanglement in real-time.
  arXiv  Detail & Related papers  (2021-02-24T20:51:25Z)
• A Convolutional Neural Network based Cascade Reconstruction for the IceCube Neutrino Observatory [0.4282223735043171]
  Deep neural networks can be extremely powerful, and their usage is computationally inexpensive once the networks are trained. A reconstruction method based on convolutional architectures and hexagonally shaped kernels is presented. It can improve upon the reconstruction accuracy, while reducing the time necessary to run the reconstruction by two to three orders of magnitude.
  arXiv  Detail & Related papers  (2021-01-27T18:34:58Z)
• Deep-Learning-Based Kinematic Reconstruction for DUNE [7.1117771577210664]
  The Deep Underground Neutrino Experiment (DUNE) is a next-generation long-baseline neutrino oscillation experiment. We will present two CNN-based methods, 2-D and 3-D, for the reconstruction of final state particle direction and energy, as well as neutrino energy.
  arXiv  Detail & Related papers  (2020-12-11T08:15:23Z)

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.