Combining Maximum-Likelihood with Deep Learning for Event Reconstruction in IceCube

Abstract

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 from other domains. However, data in the field of physics are unique in the context of machine learning, insofar as their generation process and the laws and symmetries they abide by are usually well understood. Most commonly used deep learning architectures fail at utilizing this available information. In contrast, more traditional likelihood-based methods are capable of exploiting domain knowledge, but they are often limited by computational complexity. In this contribution, a hybrid approach is presented that utilizes generative neural networks to approximate the likelihood, which may then be used in a traditional maximum-likelihood setting. Domain knowledge, such as invariances and detector characteristics, can easily be incorporated in this approach. The hybrid approach is illustrated by the example of event reconstruction in IceCube.

arXiv commentPresented at the 37th International Cosmic Ray Conference (ICRC 2021). See arXiv:2107.06966 for all IceCube contributions

References in corpus (4)

• The IceCube Neutrino Observatory: Instrumentation and Online Systems
• Energy Reconstruction Methods in the IceCube Neutrino Telescope
• Muon Track Reconstruction and Data Selection Techniques in AMANDA
• Efficient propagation of systematic uncertainties from calibration to analysis with the SnowStorm method in IceCube

Cited by in corpus (5)

• Observation of Seven Astrophysical Tau Neutrino Candidates with IceCube
• Low Energy Event Reconstruction in IceCube DeepCore
• Improved modeling of in-ice particle showers for IceCube event reconstruction
• Detecting neutrinos in IceCube with Cherenkov light in the South Pole ice
• Refine Neutrino Events Reconstruction with BEiT-3