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

T: Fachverband Teilchenphysik

T 92: Electronics, Trigger, DAQ IV

T 92.5: Vortrag

Freitag, 20. März 2026, 10:00–10:15, KH 00.023

AI-enabled FPGA trigger for autonomous radio detection of cosmic rays — Alperen Aksoy³, Ilja Bekman³, Markus Cristinziani¹, Eric-Teunis de Boone¹, •Vesselin Dimitrov¹, Qader Dorosti¹, Chimezie Eguzo³, Stefan Heidbrink², Waldemar Stroh², Jens Winter², and Michael Ziolkowski² — ¹Experimentelle Astroteilchenphysik, Center for Particle Physics Siegen, Universität Siegen — ²Elektronikentwicklungslabor des Departments Physik, Universität Siegen — ³Peter Grünberg Institute - Integrated Computing Architectures, Forschungszentrum Jülich

Radio detection of extensive air showers induced by ultra-high-energy cosmic rays provides crucial information on their origin, composition and energy. Radio arrays detect these events, but cosmic-ray signals are exceedingly rare compared to the overwhelming radio noise and RFI. Since storing all data is not feasible, a trigger system must decide in real time which data to record. FPGAs are a fitting option for this requirement because they provide deterministic low latency and low energy consumption compared to CPUs or GPUs. In this collaborative work between the University of Siegen and the Forschungszentrum Jülich, we investigate a novel approach where a machine-learning-based trigger is implemented on an FPGA. The goal is to achieve reliable discrimination between cosmic-ray signals and background, by employing a quantized neural network with minimal latency and power consumption. We aim to validate the quantized model on an FPGA and assess resource usage, latency, power consumption and trigger efficiency, while strongly reducing the false-trigger rate for cosmic-ray events.

Keywords: FPGA; cosmic rays; machine learning; radio detection; trigger