Journal
JOURNAL OF INSTRUMENTATION
Volume 17, Issue 11, Pages -Publisher
IOP Publishing Ltd
DOI: 10.1088/1748-0221/17/11/P11003
Keywords
Analysis and statistical methods; Data analysis; Neutrino detectors; Particle identification methods
Categories
Funding
- U.S.A.-U.S. National Science Foundation-Office of Polar Programs
- U.S.A.-U.S. National Science Foundation-Physics Division
- U.S.A.-U.S. National Science Foundation-EPSCoR
- U.S.A.-Wisconsin Alumni Research Foundation
- U.S.A.-Center for High Throughput Computing (CHTC) at the University of Wisconsin-Madison
- U.S.A.-Open Science Grid (OSG)
- U.S.A.-Extreme Science and Engineering Discovery Environment (XSEDE)
- U.S.A.-Frontera computing project at the Texas Advanced Computing Center
- U.S.A.-U.S. Department of Energy-National Energy Research Scientific Computing Center
- U.S.A.-Particle astrophysics research computing center at the University of Maryland
- U.S.A.-Institute for Cyber-Enabled Research at Michigan State University
- U.S.A.-Astroparticle physics computational facility at Marquette University
- Belgium -Funds for Scientific Research (FRS-FNRS and FWO)
- Belgium -FWO Odysseus and Big Science programmes
- Belgium -Belgian Federal Science Policy Office (Belspo)
- Germany -Bundesministerium fur Bildung und Forschung (BMBF)
- Germany-Deutsche Forschungsgemeinschaft (DFG)
- Germany-Helmholtz Alliance for Astroparticle Physics (HAP)
- Germany-Initiative and Networking Fund of the Helmholtz Association
- Germany-Deutsches Elektronen Synchrotron (DESY)
- Germany-High Performance Computing cluster of the RWTH Aachen
- Sweden -Swedish Research Council
- Sweden -Swedish Polar Research Secretariat
- Sweden -Swedish National Infrastructure for Computing (SNIC)
- Sweden -Knut and AliceWallenberg Foundation
- Australia -Australian Research Council
- Canada -Natural Sciences and Engineering Research Council of Canada
- Canada -Calcul Quebec
- Canada -Compute Ontario
- Canada -Canada Foundation for Innovation
- Canada -WestGrid
- Canada -Compute Canada
- Denmark-Villum Fonden
- Denmark- Carlsberg Foundation
- Denmark-European Commission
- New Zealand -Marsden Fund
- Japan -Japan Society for Promotion of Science (JSPS)
- Japan -Institute for Global Prominent Research (IGPR) of Chiba University
- Korea-National Research Foundation of Korea (NRF)
- Switzerland-Swiss National Science Foundation (SNSF)
- United Kingdom-Department of Physics, University of Oxford
Ask authors/readers for more resources
IceCube, a cubic-kilometer array of optical sensors, uses a Graph Neural Network (GNN) to classify and reconstruct events, increasing the signal efficiency and improving the resolution.
IceCube, a cubic-kilometer array of optical sensors built to detect atmospheric and astrophysical neutrinos between 1 GeV and 1 PeV, is deployed 1.45 km to 2.45 km below the surface of the ice sheet at the South Pole. The classification and reconstruction of events from the in-ice detectors play a central role in the analysis of data from IceCube. Reconstructing and classifying events is a challenge due to the irregular detector geometry, inhomogeneous scattering and absorption of light in the ice and, below 100 GeV, the relatively low number of signal photons produced per event. To address this challenge, it is possible to represent IceCube events as point cloud graphs and use a Graph Neural Network (GNN) as the classification and reconstruction method. The GNN is capable of distinguishing neutrino events from cosmic-ray backgrounds, classifying different neutrino event types, and reconstructing the deposited energy, direction and interaction vertex. Based on simulation, we provide a comparison in the 1 GeV-100 GeV energy range to the current state-of-the-art maximum likelihood techniques used in current IceCube analyses, including the effects of known systematic uncertainties. For neutrino event classification, the GNN increases the signal efficiency by 18% at a fixed background rate, compared to current IceCube methods. Alternatively, the GNN offers a reduction of the background (i.e. false positive) rate by over a factor 8 (to below half a percent) at a fixed signal efficiency. For the reconstruction of energy, direction, and interaction vertex, the resolution improves by an average of 13%-20% compared to current maximum likelihood techniques in the energy range of 1 GeV-30 GeV. The GNN, when run on a GPU, is capable of processing IceCube events at a rate nearly double of the median IceCube trigger rate of 2.7 kHz, which opens the possibility of using low energy neutrinos in online searches for transient events.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available