Gießen 2024 – scientific programme

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

HK: Fachverband Physik der Hadronen und Kerne

HK 20: Astroparticle Physics II

HK 20.5: Talk

Tuesday, March 12, 2024, 17:00–17:15, HBR 19: C 103

Development of a Neural-Network-Based Event Reconstruction for the RadMap Telescope — •Luise Meyer-Hetling¹, Liesa Eckert¹, Peter Hinderberger¹, Martin J. Losekamm¹, Stephan Paul¹, Thomas Pöschl³, and Sebastian Rückerl² — ¹School of Natural Sciences, Technical University of Munich, Garching, Germany — ²School of Engineering and Design, Technical University of Munich, Ottobrunn, Germany — ³CERN, Geneva, Switzerland

The RadMap Telescope is a compact multi-purpose radiation detector developed to provide near real-time monitoring of the radiation aboard crewed un uncrewed spacecrafts. A first prototype is currently deployed on the International Space Station for an in-orbit demonstration of the instrument's capabilities. Its main sensor consists of a stack of scintillating-plastic fibers whose perpendicular configuration allows the three-dimensional tracking and identification of cosmic-ray ions by reconstruction of their energy-loss profiles. We trained a set of neural networks on simulated detector data and assembled them into an analysis framework to perform an event-by-event reconstruction of track parameters, ion type and energy. In addition to our current offline analysis, we plan to implement the framework on the instrument's flight computer to analyze measurements without requiring the transmission of raw data to Earth. In this contribution, we will describe our neural-network-based reconstruction methods and present first results. Our work is funded by the German Research Foundation (DFG, project number 414049180) and under Germany's Excellence Strategy - EXC2094 - 390783311.

Keywords: Cosmic Rays; Radiation Monitoring; Machine Learning; Particle Tracking; Bragg Curve Spectroscopy