Real-time graph neural networks on FPGAs for the Belle II electromagnetic calorimeter

Abstract

We present the development and evaluation of a real-time Graph Neural Network-based trigger module for the electromagnetic calorimeter of the Belle~II experiment at the SuperKEKB collider. The algorithm processes calorimeter trigger cells as graph nodes to perform clustering, feature extraction, and per-cluster signal classification with deterministic latency. The model predicts cluster positions and energies and provides a signal classification score, enabling a more flexible clustering strategy than the baseline trigger algorithm. Implemented on an FPGA and integrated into the Belle~II trigger readout infrastructure for synchronous operation, the system sustains the MHz trigger throughput with an end-to-end latency of $3.168\mu$s. The performance is evaluated on simulated events and collision data. The energy resolution is comparable to the baseline trigger, while the position resolution for high-energy clusters improves by up to 18% in the central detector region. Cluster purity increases by up to 20% at low energies for isolated clusters, and cluster efficiency improves by up to 20% for overlapping clusters. The signal classifier enables additional background suppression at fixed signal retention. These results demonstrate a first step towards GNN-based real-time reconstruction on FPGAs in a collider trigger. While the end-to-end latency exceeds the trigger decision budget, the system already sustains full operational conditions with 100% uptime.

References in corpus (23)

• The Dark Photon
• Revised constraints and Belle II sensitivity for visible and invisible axion-like particles
• Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors
• Matching perturbative and Parton Shower corrections to Bhabha process at flavour factories
• Graph Neural Networks in Particle Physics
• Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics
• Search for Axion-Like Particles produced in $e^{+}{e}^{-}$ collisions at Belle II
• Invisible and displaced dark matter signatures at Belle II
• Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics
• Graph Neural Networks for Particle Tracking and Reconstruction
• Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph and image data
• Belle II sensitivity to long-lived dark photons
• Measurements of Beam Backgrounds in SuperKEKB Phase 2
• Measured and projected beam backgrounds in the Belle II experiment at the SuperKEKB collider
• Measurement of the integrated luminosity of data samples collected during 2019-2022 by the Belle II experiment
• LL-GNN: Low Latency Graph Neural Networks on FPGAs for High Energy Physics
• Photon Reconstruction in the Belle II Calorimeter Using Graph Neural Networks
• Real-time Graph Building on FPGAs for Machine Learning Trigger Applications in Particle Physics
• Design of the Global Reconstruction Logic in the Belle II Level-1 Trigger system
• Deep learning techniques for energy clustering in the CMS ECAL
• Searching Dark Photons using displaced vertices at Belle II -- with backgrounds
• Search for a Dark Higgs Boson Produced in Association with Inelastic Dark Matter at the Belle II Experiment
• Using graph neural networks to reconstruct charged pion showers in the CMS High Granularity Calorimeter