A Multi-Stage Machine Learning Approach to Cosmic Ray Detection in the RNO-G Experiment

The Radio Neutrino Observatory-Greenland (RNO-G), deployed at Summit Station, Greenland, aims to detect ultra-high-energy (UHE) neutrinos. To maximize sensitivity, RNO-G operates with low trigger thresholds, leading to data dominated by background noise, including thermal and anthropogenic sources. A potential additional background source is associated with cosmic ray signals coming from cosmic ray-induced air-showers and further sub-showers produced in the ice, which can mimic neutrino signals. Understanding these events is crucial for improving event classification in future neutrino searches. To address this, two parallel approaches are being developed within the collaboration. The primary method employs a linear discriminant analysis, while an exploratory approach, which this presentation is focused on, utilizes a three-stage event filtering scheme. This scheme sequentially applies a cut-based thermal noise filter, followed by machine learning classifiers—a boosted decision tree (BDT) and a convolutional neural network (CNN)—trained on both simulated cosmic-ray candidates and real background-dominated data. The method effectively rejects background while preserving high signal efficiency. The presentation showcases this powerful machine learning based analysis, highlighting its performance in distinguishing deep cosmic-ray candidates from other types of impulsive background. These results will inform future RNO-G neutrino searches, enhancing its capability to isolate astrophysical neutrino events.

Authors

Publication Details

Published
2025-09-23
DOI
https://doi.org/10.22323/1.501.0319
Primary Topic
Dark Matter and Cosmic Phenomena
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A Multi-Stage Machine Learning Approach to Cosmic Ray Detection in the RNO-G Experiment

Rob Young, Felix Schlüter, O. Schölten, Claudio Kopper et al.
Dark Matter and Cosmic Phenomena
article

A Multi-Stage Machine Learning Approach to Cosmic Ray Detection in the RNO-G Experiment

Rob Young, Felix Schlüter, O. Schölten, Claudio Kopper, Honglian Gui, Sanyukta Agarwal, Dawn Williams, J. Hanson, K. Hughes, Kenneth Couberly, A. Zink, P. Allison, Sjoerd Bouma, T. Glüsenkamp, Aishwarya Vijai, M. Kowalski, Bob Oeyen, Pawan Giri, S. Toscano, Enrique Huesca Santiago, Christian Gläser, O. Botner, Simon De Kockere, Cosmin Deaconu, James H. Tutt, Dieder Van den Broeck, T. Karg, Jakob Henrichs, A. G. Vieregg, Eric Oberla, Jethro Stoffels, S. Buitink, M. Marsee, A. Nozdrina, A. Nelles, Dirk Ryckbosch, Christian Hornhuber, Noppadol Punsuebsay, K. Helbing, S. Hallmann, Marco Stein Muzio, Christoph Welling, Bryan L. Hendricks, Alexander Novikov, P. J. Windischhofer, Abigail Bishop, Allan Hallgren, michael Korntheuer, Ilya Kravchenko, Adam Rifaie, R. Lahmann, Krijn de Vries, Mohammad Ful Hossain Seikh, Nils Heyer, Simon Chiche, J. L. Kelley, Katharine Mulrey, Annanay Jaitly, Martin Langgård Ravn, Nathaniel Alden, J. A. Aguilar, Albrecht Karle, Juliana Stachurska, C.-H. Liu, Delia Tosi, Brian Clark, Lilly Pyras, Stephanie Wissel, Michael Betts, Jonathan H. Chan, Dave Besson, D. Seckel, Alan Coleman, Ryan Krebs, N. van Eijndhoven, Shoukat Ali, Ruben Camphyn, Mirko Kugelmeier, Zeynep Su Selcuk
article en

Abstract

The Radio Neutrino Observatory-Greenland (RNO-G), deployed at Summit Station, Greenland, aims to detect ultra-high-energy (UHE) neutrinos. To maximize sensitivity, RNO-G operates with low trigger thresholds, leading to data dominated by background noise, including thermal and anthropogenic sources. A potential additional background source is associated with cosmic ray signals coming from cosmic ray-induced air-showers and further sub-showers produced in the ice, which can mimic neutrino signals. Understanding these events is crucial for improving event classification in future neutrino searches. To address this, two parallel approaches are being developed within the collaboration. The primary method employs a linear discriminant analysis, while an exploratory approach, which this presentation is focused on, utilizes a three-stage event filtering scheme. This scheme sequentially applies a cut-based thermal noise filter, followed by machine learning classifiers—a boosted decision tree (BDT) and a convolutional neural network (CNN)—trained on both simulated cosmic-ray candidates and real background-dominated data. The method effectively rejects background while preserving high signal efficiency. The presentation showcases this powerful machine learning based analysis, highlighting its performance in distinguishing deep cosmic-ray candidates from other types of impulsive background. These results will inform future RNO-G neutrino searches, enhancing its capability to isolate astrophysical neutrino events.

National Science Foundation, European Commission, Fonds De La Recherche Scientifique - FNRS, Fonds Wetenschappelijk Onderzoek, Vetenskapsrådet, British Antarctic Survey, Office of Experimental Program to Stimulate Competitive Research
Openalex Percentile: Top 89%
Dark Matter and Cosmic Phenomena
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.