arXiv subjects

M. Neu

Publications and source records attributed to M. Neu.

5 recordsLinked to original sources

arXiv2026

Commissioning and Low Latency Operation of the Graph Neural Network Electromagnetic Calorimeter Trigger at the Belle II Experiment

We present the commissioning and operation of the Graph Neural Network Electromagnetic Calorimeter Trigger Module (GNN-ETM) of the Belle II experiment at the SuperKEKB collider. The GNN-ETM processes calorimeter trigger cells as graph nodes to perform clustering and feature extraction. We fully integrate the system with the successive stages of the first-level trigger, develop slow-control drivers, and add online monitoring capabilities. We optimise the existing FPGA-based architecture through hardware-algorithm co-design, achieving an overall system latency of 1.053 us. Our hardware implementation is validated through register-transfer-level simulations, achieving bit-accurate agreement with the offline reference model. Online monitoring enables the measurement of instantaneous trigger rates, providing a quantitative basis for trigger-level performance studies. In summary, we report on the GNN-ETM as a fully operational, low-latency trigger module with online control and monitoring capabilities, compatible with the latency requirements of the Belle II first-level trigger system.

hep-ex↗

arXiv2026

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

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.

physics.ins-det↗

arXiv2025

Development of Deep Neural Network First-Level Hardware Track Trigger for the Belle II Experiment

The Belle II experiment at the SuperKEKB accelerator is designed to explore physics beyond the Standard Model with unprecedented luminosity. As the beam intensity increased, the experiment faced significant challenges due to higher beam-induced background, leading to a high trigger rate and placing limitations on further luminosity increases. To address this problem, we developed trigger logic for tracking using deep neural network (DNN) technology on an FPGA for the Belle II hardware trigger system, employing high-level synthesis techniques. By leveraging drift time and hit pattern information from the Central Drift Chamber and incorporating a simplified self-attention architecture, the DNN track trigger significantly improves track reconstruction performance at the hardware level. Compared to the existing neural track trigger, our implementation reduces the total track trigger rate by 37% while improving average efficiency for the signal tracks from 96% to 98% for charged tracks with transverse momentum > 0.3 GeV. This upgrade ensures the long-term viability of the Belle II data acquisition system as luminosity continues to increase.

physics.ins-det↗

arXiv2025

Design of the Global Reconstruction Logic in the Belle II Level-1 Trigger system

The Belle~II experiment is designed to search for physics beyond the Standard Model by investigating rare decays at the SuperKEKB $e^{+}e^{-}$ collider. Owing to the significant beam background at high luminosity, the data acquisition system employs a hardware-based Level-1~Trigger to reduce the readout data throughput by selecting collision events of interest in real time. The Belle~II Level-1~Trigger system utilizes FPGAs to reconstruct various detector observables from the raw data for trigger decision-making. The Global Reconstruction Logic receives these processed observables from four sub-trigger systems and provides a global summary for the final trigger decision. Its logic encompasses charged particle tracking, matching between sub-triggers, and the identification of special event topologies associated with low-multiplicity decays. This article discusses the hardware devices, FPGA firmware, integration with peripheral systems, and the design and performance of the trigger algorithms implemented within the Global Reconstruction Logic.

hep-ex↗

arXiv2024

The Neural Network First-Level Hardware Track Trigger of the Belle II Experiment

We describe the principles and performance of the first-level ("L1") hardware track trigger of Belle II, based on neural networks. The networks use as input the results from the standard Belle II trigger, which provides "2D" track candidates in the plane transverse to the electron-positron beams. The networks then provide estimates for the origin of the 2D track candidates in direction of the colliding beams ("$z$-vertex"), as well as their polar emission angles $\theta$. Given the $z$-vertices of the "neural" tracks allows identifying events coming from the collision region ($z \approx 0$), and suppressing the overwhelming background from outside by a suitable cut $d$. Requiring $|z| < d$ for at least one neural track in an event with two or more 2D candidates will set an L1 trigger. The networks also enable a minimum bias trigger, requiring a single 2D track candidate validated by a neural track with a momentum larger than 0.7 GeV in addition to the $|z|$ condition. The momentum of the neural track is derived with the help of the polar angle $\theta$.

hep-ex↗