Related papers: Graph Neural Networks for Low-Energy Event Classif…
The IceCube Neutrino Observatory is a cubic-kilometer detector located in the Antarctic ice at the geographic South Pole. It reads out over 5,000 photomultiplier tubes (PMTs) to detect Cherenkov light produced by secondary particles,…
This work presents a novel approach to water Cherenkov neutrino detector event reconstruction and classification. Three forms of a Convolutional Neural Network have been trained to reject cosmic muon events, classify beam events, and…
The IceCube Neutrino Observatory, which instruments 1$\,$km$^3$ of clear ice at the geographic South Pole, was mainly designed to detect particles with energies in the multi-GeV to PeV range. Due to ice temperatures between $-20^\circ$C to…
The IceCube neutrino spectrum shows a flux which falls of as $E^{-2}$ for sub PeV energies but there are no neutrino events observed above $\sim 3$ PeV. In particular the Glashow resonance expected at 6.3 PeV is not seen. We examine a…
The IceCube Neutrino Observatory, located at the geographic South Pole, comprises a surface component, IceTop, and an optical in-ice array. This unique com\-bi\-na\-tion allows for coincident measurements of low-energy ($\sim \rm{GeV}$) and…
IceCube is an all-flavor, cubic kilometer neutrino telescope currently under construction in the deep glacial ice at the South Pole. Its embedded optical sensors detect Cherenkov light from charged particles produced in neutrino…
Machine learning methods have a long history of applications in high energy physics (HEP). Recently, there is a growing interest in exploiting these methods to reconstruct particle signatures from raw detector data. In order to benefit from…
The field of deep learning has become increasingly important for particle physics experiments, yielding a multitude of advances, predominantly in event classification and reconstruction tasks. Many of these applications have been adopted…
A graph neural network (GNN) for image understanding based on multiple cues is proposed in this paper. Compared to traditional feature and decision fusion approaches that neglect the fact that features can interact and exchange information,…
Edge vision systems combining sensing and embedded processing promise low-latency, decentralized, and energy-efficient solutions that forgo reliance on the cloud. As opposed to conventional frame-based vision sensors, event-based cameras…
IceCube-Gen2 is a proposed neutrino observatory at the South Pole that will build on the success of IceCube and will also serve as a unique detector for cosmic-ray air showers. Analogous to the IceTop surface array over IceCube's deep…
Recent work has demonstrated that geometric deep learning methods such as graph neural networks (GNNs) are well suited to address a variety of reconstruction problems in high energy particle physics. In particular, particle tracking data is…
Event cameras attract researchers' attention due to their low power consumption, high dynamic range, and extremely high temporal resolution. Learning models on event-based object classification have recently achieved massive success by…
Neutrino Events Reconstruction has always been crucial for IceCube Neutrino Observatory. In the Kaggle competition "IceCube -- Neutrinos in Deep Ice", many solutions use Transformer. We present ISeeCube, a pure Transformer model based on…
The recent detection of TeV neutrino sources by the IceCube Neutrino Observatory demonstrates the detector's advanced capabilities in detecting high-energy astrophysical neutrinos. At lower energies, down to the GeV range, a variety of…
Recent observations of GeV gamma-rays from novae have led to a paradigm shift in the understanding of these objects. While it is now believed that shocks contribute significantly to the energy budget of novae, it is still unknown if the…
The growing luminosity frontier at the Large Hadron Collider is challenging the reconstruction and analysis of particle collision events. Increased particle multiplicities are straining latency and storage requirements at the data…
An initial study of the extremely high energy (EHE) physics capabilityof the IceCube neutrino observatory is demonstrated by considering a GZK mechanism neutrino production model, which is a guaranteed source for EHE neutrinos. We study EHE…
To read the final version please go to IEEE TGRS on IEEE Xplore. Convolutional neural networks (CNNs) have been attracting increasing attention in hyperspectral (HS) image classification, owing to their ability to capture spatial-spectral…
Deep learning tools are being used extensively in high energy physics and are becoming central in the reconstruction of neutrino interactions in particle detectors. In this work, we report on the performance of a graph neural network in…