guest ::
| Home > Publications database > Hardware-efficient neural networks for FPGA-based radio triggering of extensive air showers |
| Home > Publications database > Hardware-efficient neural networks for FPGA-based radio triggering of extensive air showers |
| Preprint | FZJ-2026-05057 |
; ; ; ; ; ; ; ; ;
2026
SISSA Medialab Trieste, Italy
This record in other databases:
Please use a persistent id in citations: doi:10.22323/1.538.0034
Abstract: We present a hardware-efficient hybrid trigger for FPGA-based radio detection of extensive air showers. The hybrid design consists of a lightweight denoiser that cleans raw ADC traces anda compact classifier that operates on the denoised output, enabling robust near-threshold pulse detection in high-interference environments. Both neural networks are trained quantization-aware.Signals are generated from detector-folded CoREAS/CORSIKA simulations and embedded intomeasured noise to form a realistic benchmark. The trigger reaches an AUC of 0.992 while fittingcomfortably within the resource budget of a Zynq-7000 Z-7020, with microsecond-scale latencyand sub-watt power consumption. RTL validation confirms agreement between the fixed-pointhardware and the quantized software model, demonstrating that neural denoising combined withclassification provides reliable, low-cost radio triggering in noisy environments.
|
The record appears in these collections: |
