SpikePID: Real-Time Neuromorphic Cluster Counting in Future Drift Chambers
Abstract
Cluster counting (dN/dx) measures discrete ionization occurrences along a charged particle track traversing a gaseous medium and is currently being proposed to serve particle identification (PID) in next-generation drift chambers, as it is expected to offer higher separation power than the traditional approach based on the ionization energy loss measurement (dE/dx), which has intrinsically larger statistical fluctuations. However, measuring dN/dx in drift chambers proposed for future colliders requires high-resolution waveforms, which result in very large data rates. Running the reconstruction at the edge would drastically reduce the bandwidth required to transmit data off the detector. In this paper, we introduce SpikePID, a neuromorphic computing approach applying spiking neural networks (SNNs) to this task due to their inherently sparse computing and processing nature. We show that an SNN with only 529 parameters improves the kaon-pion separation power by 17% over the traditional derivative-based method and by 4% over an MLP that has 8.6× more parameters. When synthesized to an FPGA, it uses an order of magnitude fewer resources than the MLP, and has an inference latency compatible with the constraints of future collider experiments, making the SNN an excellent algorithmic candidate for real-time data readout in future drift chambers.
Related
- Approximate Counting for Mixed p-Spin Glasses in Weak External Fields via Cluster Expansion
- From Hits to Tracks: A BERT-based Tracking Model for Track Reconstruction in Drift Chambers
- Optical imaging in dual-phase xenon time projection chambers for neutrinoless double beta decay searches
- Construction and Performance of the sMDT Precision Muon Tracking Chambers for ATLAS at the HL-LHC
- Charge Collection Efficiency in Air-Vented Plane-Parallel Ionisation Chambers at Ultra-High Dose Rates: A Self-Consistent Garfield++ Monte Carlo Model Including Space-Charge Effects and Ion Recombination
BibTeX
@misc{tsoi2026spikepid,
title = {{SpikePID: Real-Time Neuromorphic Cluster Counting in Future Drift Chambers}},
author = {Ho Fung Tsoi and Kam Wai Lai and Dylan Rankin},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.00104},
eprint = {2611.00104},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.00104},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - SpikePID: Real-Time Neuromorphic Cluster Counting in Future Drift Chambers
AU - Ho Fung Tsoi
AU - Kam Wai Lai
AU - Dylan Rankin
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.00104
UR - https://arxiv.org/abs/2611.00104
AB - Cluster counting (dN/dx) measures discrete ionization occurrences along a charged particle track traversing a gaseous medium and is currently being proposed to serve particle identification (PID) in next-generation drift chambers, as it is expected to offer higher separation power than the traditional approach based on the ionization energy loss measurement (dE/dx), which has intrinsically larger statistical fluctuations. However, measuring dN/dx in drift chambers proposed for future colliders requires high-resolution waveforms, which result in very large data rates. Running the reconstruction at the edge would drastically reduce the bandwidth required to transmit data off the detector. In this paper, we introduce SpikePID, a neuromorphic computing approach applying spiking neural networks (SNNs) to this task due to their inherently sparse computing and processing nature. We show that an SNN with only 529 parameters improves the kaon-pion separation power by 17% over the traditional derivative-based method and by 4% over an MLP that has 8.6× more parameters. When synthesized to an FPGA, it uses an order of magnitude fewer resources than the MLP, and has an inference latency compatible with the constraints of future collider experiments, making the SNN an excellent algorithmic candidate for real-time data readout in future drift chambers.
ER -