AI-based particle track identification in scintillating fibres read out with imaging sensors

2024-10-14

arXiv.org

AI Summary

In high-energy physics experiments, SPAD-array-based imaging of scintillating fibers suffers from overwhelming background noise, sparse particle-track frames, and challenges in real-time identification. To address this, we propose an unsupervised anomaly detection method based on a lightweight variational autoencoder (VAE), trained exclusively on clean background frames. The model enables end-to-end online triggering, automatically isolating particle-track-containing frames from background-dominated ones. Our key innovation lies in the first successful adaptation of a lightweight VAE to scintillating-fiber–SPAD imaging systems—requiring no labeled data, achieving low latency, and exhibiting strong robustness against noise and detector nonuniformities. Evaluated on real experimental data, the method achieves high signal-frame detection accuracy, meets real-time throughput requirements, and demonstrates feasibility for FPGA/ASIC hardware deployment. This significantly enhances trigger efficiency and energy efficiency in high-energy physics experiments.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Motion & Tracking

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

This paper presents the development and application of an AI-based method for particle track identification using scintillating fibres read out with imaging sensors. We propose a variational autoencoder (VAE) to efficiently filter and identify frames containing signal from the substantial data generated by SPAD array sensors. Our VAE model, trained on purely background frames, demonstrated a high capability to distinguish frames containing particle tracks from background noise. The performance of the VAE-based anomaly detection was validated with experimental data, demonstrating the method's ability to efficiently identify relevant events with rapid processing time, suggesting a solid prospect for deployment as a fast inference tool on hardware for real-time anomaly detection. This work highlights the potential of combining advanced sensor technology with machine learning techniques to enhance particle detection and tracking.

Problem

• AI-based particle track identification in scintillating fibres
• Filtering signal frames from SPAD array sensor data
• Real-time anomaly detection using VAE for particle tracks

Innovation

• AI-based particle track identification
• Variational autoencoder for signal filtering
• Real-time anomaly detection with VAE