Hardware-aware quantum attention for fast radio burst identification
Abstract
Fast radio bursts (FRBs) are millisecond-duration extragalactic pulses whose discovery requires searches over large signal-parameter spaces and the rejection of candidate sets dominated by radio-frequency interference and noise. Integrating quantum processors into FRB searches requires a workflow connecting telescop data to hardware-compatible models. Here we develop a pipeline that converts raw search-mode PSRFITS data into dynamic-spectrum segments and identifies FRB-like signals using a hybrid Quantum Vision Transformer (QViT). On labelled FAST data, the selected QViT achieves a mean accuracy of 94.00% and recall of 98.30%, with similar performance to a compact classical Vision Transformer. Recall reaches 97.11% on an FRB source excluded from training and model selection. Real-device execution on 82 segments yields a mean simulator-hardware Hellinger fidelity of 0.9161 +/- 0.0074. The workflow connects raw telescope data to quantum-assisted identification and provides an experimental basis for assessing the measurement requirements that must be addressed before survey-scale deployment.
Related
- Hardware-efficient neural networks for FPGA-based radio triggering of extensive air showers
- FARSim: a fast RF-chain-aware trigger-screening surrogate for radio detection of ultra-high-energy cosmic rays
- Through a glass, darkly: a combined framework for estimating fast radio burst host galaxy and population properties in an era of uncertain host identification
- Extending the Pulsar radio population through Quantum Vacuum Cherenkov Emission
- Radio ghosts: Radio polarimetry study of newly discovered cluster minihalo candidates or radio tailed galaxies
BibTeX
@misc{he2026hardwareaware,
title = {{Hardware-aware quantum attention for fast radio burst identification}},
author = {Li He and Xuan Yang and Feng Xiong and Songbo Zhang and Qiuhao Chen and Yuchen He and Yunxiang Yang and Jun Lu and Claudio Furtado and Amilcar R. Queiroz and Xinping Deng and Yang Wu and Xuefeng Wu},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.15108},
eprint = {2609.15108},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.15108},
}
RIS
TY - UNPB
TI - Hardware-aware quantum attention for fast radio burst identification
AU - Li He
AU - Xuan Yang
AU - Feng Xiong
AU - Songbo Zhang
AU - Qiuhao Chen
AU - Yuchen He
AU - Yunxiang Yang
AU - Jun Lu
AU - Claudio Furtado
AU - Amilcar R. Queiroz
AU - Xinping Deng
AU - Yang Wu
AU - Xuefeng Wu
PY - 2026
DA - 2026/09/14
PB - arXiv
DO - 10.48550/arxiv.2609.15108
UR - https://arxiv.org/abs/2609.15108
AB - Fast radio bursts (FRBs) are millisecond-duration extragalactic pulses whose discovery requires searches over large signal-parameter spaces and the rejection of candidate sets dominated by radio-frequency interference and noise. Integrating quantum processors into FRB searches requires a workflow connecting telescop data to hardware-compatible models. Here we develop a pipeline that converts raw search-mode PSRFITS data into dynamic-spectrum segments and identifies FRB-like signals using a hybrid Quantum Vision Transformer (QViT). On labelled FAST data, the selected QViT achieves a mean accuracy of 94.00% and recall of 98.30%, with similar performance to a compact classical Vision Transformer. Recall reaches 97.11% on an FRB source excluded from training and model selection. Real-device execution on 82 segments yields a mean simulator-hardware Hellinger fidelity of 0.9161 +/- 0.0074. The workflow connects raw telescope data to quantum-assisted identification and provides an experimental basis for assessing the measurement requirements that must be addressed before survey-scale deployment.
ER -