An official website of the United States government
Abstract 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.
more »
« less
Low energy event classification in IceCube using boosted decision trees
Abstract The DeepCore sub-array within the IceCube Neutrino Observatory is a densely instrumented region of Antarctic ice designed to observe atmospheric neutrino interactions above 5 GeV via Cherenkov radiation. An essential aspect of any neutrino oscillation analysis is the ability to accurately identify the flavor of neutrino events in the detector. This task is particularly difficult at low energies when very little light is deposited in the detector. Here we discuss the use of machine learning to perform event classification at low energies in IceCube using a boosted decision tree (BDT). A BDT is trained using reconstructed quantities to identify track-like events, which result from muon neutrino charged current interactions. This new method improves the accuracy of particle identification compared to traditional classification methods which rely on univariate straight cuts.
more »
« less
- Award ID(s):
- 1913607
- PAR ID:
- 10349667
- Date Published:
- Journal Name:
- Journal of Instrumentation
- Volume:
- 16
- Issue:
- 12
- ISSN:
- 1748-0221
- Page Range / eLocation ID:
- C12007
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Name that Neutrinois a citizen science project where volunteers aid in classification of events for the IceCube Neutrino Observatory, an immense particle detector at the geographic South Pole. From March 2023 to September 2023, volunteers did classifications of videos produced from simulated data of both neutrino signal and background interactions.Name that Neutrinoobtained more than 128,000 classifications by over 1800 registered volunteers that were compared to results obtained by a deep neural network machine-learning algorithm. Possible improvements for bothName that Neutrinoand the deep neural network are discussed.more » « less
-
The IceCube Neutrino Observatory at the South Pole has measured the diffuse astrophysical neutrino flux up to ~PeV energies and is starting to identify first point source candidates. The next generation facility, IceCube-Gen2, aims at extending the accessible energy range to EeV in order to measure the continuation of the astrophysical spectrum, to identify neutrino sources, and to search for a cosmogenic neutrino flux. As part of IceCube-Gen2, a radio array is foreseen that is sensitive to detect Askaryan emission of neutrinos beyond ~30 PeV. Surface and deep antenna stations have different benefits in terms of effective area, resolution, and the capability to reject backgrounds from cosmic-ray air showers and may be combined to reach the best sensitivity. The optimal detector configuration is still to be identified. This contribution presents the full-array simulation efforts for a combination of deep and surface antennas, and compares different design options with respect to their sensitivity to fulfill the science goals of IceCube-Gen2.more » « less
-
Abstract The Pandora Software Development Kit and algorithm libraries perform reconstruction of neutrino interactions in liquid argon time projection chamber detectors. Pandora is the primary event reconstruction software used at the Deep Underground Neutrino Experiment, which will operate four large-scale liquid argon time projection chambers at the far detector site in South Dakota, producing high-resolution images of charged particles emerging from neutrino interactions. While these high-resolution images provide excellent opportunities for physics, the complex topologies require sophisticated pattern recognition capabilities to interpret signals from the detectors as physically meaningful objects that form the inputs to physics analyses. A critical component is the identification of the neutrino interaction vertex. Subsequent reconstruction algorithms use this location to identify the individual primary particles and ensure they each result in a separate reconstructed particle. A new vertex-finding procedure described in this article integrates a U-ResNet neural network performing hit-level classification into the multi-algorithm approach used by Pandora to identify the neutrino interaction vertex. The machine learning solution is seamlessly integrated into a chain of pattern-recognition algorithms. The technique substantially outperforms the previous BDT-based solution, with a more than 20% increase in the efficiency of sub-1 cm vertex reconstruction across all neutrino flavours.more » « less
-
The IceCube Neutrino Observatory opened the window on high-energy neutrino astronomy by confirming the existence of PeV astrophysical neutrinos and identifying the first compelling astrophysical neutrino source in the blazar TXS0506+056. Planning is underway to build an enlarged detector, IceCube-Gen2, which will extend measurements to higher energies, increase the rate of observed cosmic neutrinos and provide improved prospects for detecting fainter sources. IceCube-Gen2 is planned to have an extended in-ice optical array, a radio array at shallower depths for detecting ultra-high-energy (>100 PeV) neutrinos, and a surface component studying cosmic rays. In this contribution, we will discuss the simulation of the in-ice optical component of the baseline design of the IceCube-Gen2 detector, which foresees the deployment of an additional ~120 new detection strings to the existing 86 in IceCube over ~7 Antarctic summer seasons. Motivated by the phased construction plan for IceCube-Gen2, we discuss how the reconstruction capabilities and sensitivities of the instrument are expected to progress throughout its deployment.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1088/1748-0221/16/12/C12007
