Gießen 2024 – wissenschaftliches Programm

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

HK: Fachverband Physik der Hadronen und Kerne

HK 54: Computing II

HK 54.1: Vortrag

Mittwoch, 13. März 2024, 17:30–17:45, HBR 19: C 103

Real-time calibrations for future detectors at FAIR — •Valentin Kladov^1,2, Johan Messchendorp², and James Ritman^1,2,3 — ¹Ruhr-Universität Bochum — ²GSI Helmholtzzentrum fur Schwerionenforschung GmbH — ³Forschungszentrum Jülich

The online data processing of the next generation of experiments, such as those conducted at FAIR, requires a reliable reconstruction of event topologies and, therefore, will depend heavily on in-situ calibration procedures. In this study we present a neural network-based tool designed to provide real-time predictions of calibration constants, which rely on continuously available environmental data. To enhance regularization, we incorporate information about previous environmental states into the Long Short-Term Memory (LSTM) architecture. LSTM is combined with Graph Convolutions to facilitate predictions across multiple channels simultaneously and to account for correlations between the channels. A proof-of-principle of this approach has been demonstrated using data from the Drift Chambers of the HADES detector obtained during the February 2022 experiment. Our method demonstrated the ability to provide fast and stable calibration predictions with a precision comparable to that obtained using traditional offline, time-consuming approaches. We plan to apply the proposed methodology in a real-time experimental setting during the next HADES beam time scheduled for Feb-Mar 2024.

Keywords: online calibration; FAIR; experiment control; neural network