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

AKPIK: Arbeitskreis Physik, moderne Informationstechnologie und Künstliche Intelligenz

AKPIK 4: Deep Learning

AKPIK 4.9: Vortrag

Donnerstag, 24. März 2022, 18:15–18:30, AKPIK-H13

Reconstruction of primary particle energy from data taken by the Surface Detector of the Pierre Auger Observatory using deep neural networks — Ralf Engel, Markus Roth, Darko Veberic, David Schmidt, Steffen Hahn, and •Fiona Ellwanger for the Pierre Auger collaboration — Karlsruhe Institute of Technology (IAP), Karlsruhe, Germany

To probe physics beyond the scales of human-made accelerators with cosmic rays demands an accurate knowledge of their energy. Indirect, ground-based experiments reconstruct this primary particle energy from measurements of the emitted fluorescence light or the time-signal of the shower footprint. Using fluorescence detectors, one is able to estimate former with good accuracy. These, however, exhibit a rather low duty cycle.

At the Pierre Auger Observatory the shower footprint is measured by a regular triangular grid of water-Cherenkov detectors. Since the shower development is a very intricate process the time signals of the detectors are fairly complex. Additionally, the sheer amount of data makes it non-trivial to find hidden patterns in their spatial and temporal distributions. Neural networks provide a straightforward way of tackling such a problem doing a data-driven analysis.

With large simulation data sets we are able to train more complex networks. Systematic differences between simulations and measured data require special attention to possible biases, which are quantified. In this work, we present a neural network architecture that gives an estimate on the energy for real data.