Deep ensemble graph neural networks for probabilistic cosmic-ray direction and energy reconstruction in autonomous radio arrays
2026-02-26 • Machine Learning
Machine Learning
AI summaryⓘ
The authors created a new method using machine learning to figure out the direction and energy of very powerful cosmic rays that hit Earth, based on signals picked up by antennas. They treat the antennas like a connected network (graph) and use a special type of neural network designed for graphs. By adding physics knowledge to their model and data, they get more accurate results and need less training data. Their method can pinpoint direction with high accuracy and estimate energy with reasonable precision, even with noise in the data. They also test how sure their predictions are and check if the method works well even when real-world conditions change from their simulations.
Ultra-high-energy cosmic raysGraph neural networkRadio detector arraysAngular resolutionEnergy reconstructionMachine learningUncertainty estimationDomain shiftSignal processingPhysics-informed models
Authors
Arsène Ferrière, Aurélien Benoit-Lévy, Olivier Martineau-Huynh, Matías Tueros
Abstract
Using advanced machine learning techniques, we developed a method for reconstructing precisely the arrival direction and energy of ultra-high-energy cosmic rays from the voltage traces they induced on ground-based radio detector arrays. In our approach, triggered antennas are represented as a graph structure, which serves as input for a graph neural network (GNN). By incorporating physical knowledge into both the GNN architecture and the input data, we improve the precision and reduce the required size of the training set with respect to a fully data-driven approach. This method achieves an angular resolution of 0.092° and an electromagnetic energy reconstruction resolution of 16.4% on simulated data with realistic noise conditions. We also employ uncertainty estimation methods to enhance the reliability of our predictions, quantifying the confidence of the GNN's outputs and providing confidence intervals for both direction and energy reconstruction. Finally, we investigate strategies to verify the model's consistency and robustness under real life variations, with the goal of identifying scenarios in which predictions remain reliable despite domain shifts between simulation and reality.