Karlsruhe 2024 – scientific programme

Parts | Days | Selection | Search | Updates | Downloads | Help

T: Fachverband Teilchenphysik

T 16: Data, AI, Computing 1 (anomaly detection)

T 16.4: Talk

Monday, March 4, 2024, 16:45–17:00, Geb. 30.33: MTI

Neural network identification of highly inclined muons in water-Cherenkov particle detectors — •Mohsen Pourmohammad Shahvar for the Pierre-Auger collaboration — Università degli studi di Palermo, Palermo, Italy — INFN sezione di Catania, Catania, Italy

This contribution focuses on the neural network identification of highly inclined muons in water-Cherenkov detectors, akin to those utilized by the Pierre Auger Observatory. Highly inclined muons serve as a distinctive signature of air showers induced by either neutrinos or cosmic rays arriving at substantial inclinations, offering a lower background rate compared to less inclined atmospheric particles. The transition from conventional statistical approaches to machine learning methodologies is explored to discern highly inclined muons, capitalizing on their unique signatures in the temporal signal distributions of three photosensors uniformly observing the volume of a water-Cherenkov detector. By adopting machine learning, particularly neural network techniques, we seek to improve the identification of highly inclined muons, contributing to the enhancement of triggering schemas designed for detecting neutrino primaries. This study not only advances the identification of highly inclined muons but also investigates the optimization of machine learning models for their efficient recognition within the water-Cherenkov detector setup.

Keywords: Neural Network Identification; Highly Inclined Muons; Water-Cherenkov Detectors; Triggers; Neutrinos