Deep-learning-based reconstruction of the neutrino direction and energy for in-ice radio detectors

Abstract

Ultra-high-energy (UHE) neutrinos ($>10^{16}$ eV) can be measured cost-effectively using in-ice radio detection, which has been explored successfully in pilot arrays. A large radio detector is currently being constructed in Greenland with the potential to measure the first UHE neutrino, and an order-of-magnitude more sensitive detector is being planned with IceCube-Gen2. For such shallow radio detector stations, we present an end-to-end reconstruction of the neutrino energy and direction using deep neural networks (DNNs) developed and tested on simulated data. The DNN determines the energy with a standard deviation of a factor of two around the true energy ($\sigma \approx$ 0.3 in ${\log }_{10}(E)$), which meets the science requirements of UHE neutrino detectors. For the first time, we are able to predict the neutrino direction precisely for all event topologies including the complicated electron neutrino charged-current (${\nu }_e$-CC) interactions. The obtained angular resolution shows a narrow peak at $\mathcal{O}$($1^{\circ })$ with extended tails that push the 68\% quantile for non-${\nu }_e$-CC (resp. ${\nu }_e$-CC interactions) to $4^{\circ }(5^{\circ })$. This highlights the advantages of DNNs for modeling the complex correlations in radio detector data, thereby enabling measurement of neutrino energy and direction.

Replaced with published version

References in corpus (10)

• NuRadioReco: A reconstruction framework for radio neutrino detectors
• Astrophysics Uniquely Enabled by Observations of High-Energy Cosmic Neutrinos
• The ultra-high-energy neutrino-nucleon cross section: measurement forecasts for an era of cosmic EeV-neutrino discovery
• Reconstructing the neutrino energy for in-ice radio detectors
• Probing the angular and polarization reconstruction of the ARIANNA detector at the South Pole
• Detector Requirements for Model-Independent Measurements of Ultrahigh Energy Neutrino Cross Sections
• First-principle calculation of birefringence effects for in-ice radio detection of neutrinos
• Improving sensitivity of the ARIANNA detector by rejecting thermal noise with deep learning
• Measuring the Polarization Reconstruction Resolution of the ARIANNA Neutrino Detector with Cosmic Rays
• Toward the End-to-End Optimization of Particle Physics Instruments with Differentiable Programming: a White Paper

Cited by in corpus (6)

• Reconstructing the arrival direction of neutrinos in deep in-ice radio detectors
• The flavor composition of ultra-high-energy cosmic neutrinos: measurement forecasts for in-ice radio-based EeV neutrino telescopes
• Probing Quantum Gravity with Elastic Interactions of Ultra-High-Energy Neutrinos
• In-ice Askaryan Emission from Air Showers: Implications for Radio Neutrino Detectors
• Event Reconstruction for Radio-Based In-Ice Neutrino Detectors with Neural Posterior Estimation
• Deep Probabilistic Direction Prediction in 3D with Applications to Directional Dark Matter Detectors