2D Convolutional Neural Network for Event Reconstruction in IceCube DeepCore

TL;DR

This paper introduces a new convolutional neural network model tailored for IceCube DeepCore data, improving neutrino flavor identification and inelasticity reconstruction at GeV energies over traditional methods.

Contribution

The paper presents a novel CNN architecture that leverages translational symmetry in IceCube DeepCore data for enhanced neutrino event reconstruction.

Findings

Improved accuracy in flavor identification.

Enhanced inelasticity reconstruction performance.

Outperforms traditional likelihood-based methods.

Abstract

IceCube DeepCore is an extension of the IceCube Neutrino Observatory designed to measure GeV scale atmospheric neutrino interactions for the purpose of neutrino oscillation studies. Distinguishing muon neutrinos from other flavors and reconstructing inelasticity are especially difficult tasks at GeV scale energies in IceCube DeepCore due to sparse instrumentation. Convolutional neural networks (CNNs) have been found to have better success at neutrino event reconstruction than conventional likelihood-based methods. In this contribution, we present a new CNN model that exploits time and depth translational symmetry in IceCube DeepCore data and present the model's performance, specifically for flavor identification and inelasticity reconstruction.