Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

T: Fachverband Teilchenphysik

T 7: Kosmische Strahlung I

T 7.3: Vortrag

Montag, 19. März 2018, 16:35–16:50, Philo-HS7

Air Shower Reconstruction using Deep Convolutional Neural Networks at the Pierre Auger Observatory — •Jonas Glombitza, Niclas Eich, Martin Erdmann, and Lukas Geiger — III. Physikalisches Institut A, RWTH Aachen

The surface detector of the Pierre Auger Observatory measures the footprint of charged particles of ultra-high energy cosmic ray induced air showers on ground level. Reconstructing the properties of primary cosmic rays like energy and mass remains a challenging task. Recently, progress has been made in machine learning by techniques associated with deep neural networks. Applying this new techniques on air shower physics has the potential to improve the reconstruction quality.

In this talk we present AixNet, a deep convolutional network architecture, which is used to reconstruct energy, direction and the mass sensitive observable Xmax. We assess the performance of AixNet using CORSIKA based air showers, discuss network causality and outline the potential of AixNet for data applications by adversarial training methods.