Reconstruction of cosmic-ray direction and energy in radio arrays using deep ensemble graph neural networks

arXiv:2602.23321 · astro-ph.IM, cs.LG · Submitted 2026-02-26 · Read on arXiv

astro-ph.IM, cs.LG

Submitted: 2026-02-26

Updated: 2026-09-30

Terminology

• Consistency — 1× in this paper · explained in 3 episodes
• Domain Shift — 1× in this paper · explained in 4 episodes
• Graph Neural Network (GNN) — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Ultra-High-Energy Cosmic Rays: The Intersection of the Cosmic and Energy Frontiers
• AugerPrime: the Pierre Auger Observatory Upgrade
• Signal model and event reconstruction for the radio detection of inclined air showers
• Signal Model and Energy Reconstruction for the Radio Detection of Inclined Air Showers in the 50-200 MHz Frequency Band
• Simulation-Based Inference for Direction Reconstruction of Ultra-High-Energy Cosmic Rays with Radio Arrays
• Towards the Giant Radio Array for Neutrino Detection (GRAND): the GRANDProto300 and GRAND@Auger prototypes
• NUTRIG: Development of a Novel Radio Self-Trigger for GRAND
• Long-term calibration and validation of stability of the Auger Engineering Radio Array using the diffuse Galactic radio emission
• A Convolutional Neural Network based Cascade Reconstruction for the IceCube Neutrino Observatory

Related papers

• A signal dedispersion algorithm for imaging-based transient searches
• EXPO: a quantum leap in fast, wide-band X-ray polarimetry for astrophysics
• CHRONOS Science Program
• AVICA: A fully automated CASA pipeline for large volume VLBI data calibration
• Spectral Map Making with SPHEREx
• Long-Integration Magnetar Burst Observatory (LIMBO): Instrument Summary and Early FRB Rate Constraints