Hybrid neural denoising for resource-efficient near- and sub-threshold radio triggering of extensive air showers
Abstract
Autonomous radio self-triggering for extensive air showers requires strong rejection of radio-frequency interference while preserving weak pulses within station-level hardware constraints. We present a hybrid neural trigger comprising a compact waveform denoiser followed by a classifier. The method is evaluated using experimentally measured high-interference background traces and detector-folded simulated air-shower pulses produced with the Pierre Auger Offline chain, with the benchmark concentrated in the near-threshold regime. Hardware constraints are incorporated through hyperparameter optimisation, quantisation-aware training, and high-granularity fixed-point quantisation. Applying the conventional peak-envelope trigger after denoising increases its area under the receiver-operating-characteristic curve from 0.63 to 0.98. At a false-positive rate of 10^-4, the full denoiser-classifier chain retains about 41% of the held-out signal traces, compared with 27% for the classifier acting on the raw waveform and about 2% for the peak-envelope reference. The fixed-point firmware is synthesised, placed, and routed on representative field-programmable gate array targets, where it achieves timing closure with microsecond-scale latency and compact arithmetic-resource usage. These results establish hybrid neural denoising as a practical FPGA-compatible route toward radio-only triggering of weak and inclined air-shower signals in noisy environments.
Related
- Hardware-efficient neural networks for FPGA-based radio triggering of extensive air showers
- Rapid Response Triggering for Radio Transients with the SKA Observatory
- Triggering star formation by free-floating planets
- The role of major mergers in triggering super-Eddington accretion
- J-PAS: Exploring the connection between local environment and the triggering of bursty star formation in Extreme Emission Line Galaxies
BibTeX
@misc{dorosti2026hybrid,
title = {{Hybrid neural denoising for resource-efficient near- and sub-threshold radio triggering of extensive air showers}},
author = {Qader Dorosti and Alperen Aksoy and Ilja Bekman and Markus Cristinziani and Eric-Teunis de Boone and Vesselin Dimitrov and Chimezie Eguzo and Stefan Heidbrink and Stefan van Waasen and Andre Zambanini},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2605.28332},
eprint = {2605.28332},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.28332},
}
RIS
TY - UNPB
TI - Hybrid neural denoising for resource-efficient near- and sub-threshold radio triggering of extensive air showers
AU - Qader Dorosti
AU - Alperen Aksoy
AU - Ilja Bekman
AU - Markus Cristinziani
AU - Eric-Teunis de Boone
AU - Vesselin Dimitrov
AU - Chimezie Eguzo
AU - Stefan Heidbrink
AU - Stefan van Waasen
AU - Andre Zambanini
PY - 2026
DA - 2026/09/30
PB - arXiv
DO - 10.48550/arxiv.2605.28332
UR - https://arxiv.org/abs/2605.28332
AB - Autonomous radio self-triggering for extensive air showers requires strong rejection of radio-frequency interference while preserving weak pulses within station-level hardware constraints. We present a hybrid neural trigger comprising a compact waveform denoiser followed by a classifier. The method is evaluated using experimentally measured high-interference background traces and detector-folded simulated air-shower pulses produced with the Pierre Auger Offline chain, with the benchmark concentrated in the near-threshold regime. Hardware constraints are incorporated through hyperparameter optimisation, quantisation-aware training, and high-granularity fixed-point quantisation. Applying the conventional peak-envelope trigger after denoising increases its area under the receiver-operating-characteristic curve from 0.63 to 0.98. At a false-positive rate of 10^-4, the full denoiser-classifier chain retains about 41% of the held-out signal traces, compared with 27% for the classifier acting on the raw waveform and about 2% for the peak-envelope reference. The fixed-point firmware is synthesised, placed, and routed on representative field-programmable gate array targets, where it achieves timing closure with microsecond-scale latency and compact arithmetic-resource usage. These results establish hybrid neural denoising as a practical FPGA-compatible route toward radio-only triggering of weak and inclined air-shower signals in noisy environments.
ER -