Classification and Recovery of Radio Signals from Cosmic Ray Induced Air Showers with Deep Learning

Abstract

Radio emission from air showers enables measurements of cosmic particle kinematics and identity. The radio signals are detected in broadband Megahertz antennas among continuous background noise. We present two deep learning concepts and their performance when applied to simulated data. The first network classifies time traces as signal or background. We achieve a true positive rate of about 90% for signal-to-noise ratios larger than three with a false positive rate below 0.2%. The other network is used to clean the time trace from background and to recover the radio time trace originating from an air shower. Here we achieve a resolution in the energy contained in the trace of about 20% without a bias for $80\%$ of the traces with a signal. The obtained frequency spectrum is cleaned from signals of radio frequency interference and shows the expected shape.

20 pages, 13 figures, resubmitted to JINST

References in corpus (12)

• Radio detection of Cosmic-Ray Air Showers and High-Energy Neutrinos
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• Enhanced Higgs to ${\tau }^{+}{\tau }^{-}$ Searches with Deep Learning
• Radioelectric Field Features of Extensive Air Showers Observed with CODALEMA
• A Deep Learning-based Reconstruction of Cosmic Ray-induced Air Showers
• Reconstruction of the energy and depth of maximum of cosmic-ray air-showers from LOPES radio measurements
• The radio emission pattern of air showers as measured with LOFAR - a tool for the reconstruction of the energy and the shower maximum
• First Experimental Characterization of Microwave Emission from Cosmic Ray Air Showers
• Jet-Parton Assignment in ttH Events using Deep Learning
• A Development Environment for Visual Physics Analysis
• Results and Perspectives of the Auger Engineering Radio Array
• Experiment Software and Projects on the Web with VISPA

Cited by in corpus (8)

• Ultra-High-Energy Cosmic Rays: The Intersection of the Cosmic and Energy Frontiers
• Identification of Patterns in Cosmic-Ray Arrival Directions using Dynamic Graph Convolutional Neural Networks
• Machine learning study to identify collective flow in small and large colliding systems
• Anomaly detection in Astrophysics: a comparison between unsupervised Deep and Machine Learning on KiDS data
• Tunka-Rex Virtual Observatory
• Radio Detection of ultra-high-energy Cosmic-Ray Air Showers
• AI-Enhanced Self-Triggering for Extensive Air Showers: Performance and FPGA Feasibility
• Data-driven detector signal characterization with constrained bottleneck autoencoders