Event Building at the Future Circular Collider: Machine Learning Based Particle Flow and Track Reconstruction

• Name: Event Building at the Future Circular Collider: Machine Learning Based Particle Flow and Track Reconstruction , Hit-based MLPF
• EuroHPC machine used: MareNostrum 5
• Topic: Natural Science (Particle Physics)

Overview of the project

Accurate event reconstruction is essential to fully exploit the physics potential of modern particle physics experiments. Particle Flow (PF) algorithms enhance reconstruction efficiency and precision by combining information from multiple sub-detectors. In particular, high-quality track information significantly contributes to the overall performance of particle object reconstruction. Future experiments, such as the Future Circular Collider (FCC), are in active development and present new challenges for traditional, detector-specific reconstruction techniques. In response, machine learning-based approaches—notably transformer models—are emerging as powerful alternatives. These architectures offer the flexibility and robustness needed to meet the demands of R&D next-generation particle flow and tracking algorithms.

How did EPICURE support the project and what were the benefits of the support?

“EPICURE helped us to prepare our setup for multi-node training. Apart from scripts for launching multi-node jobs with slurm, EPICURE supported us in making our code robust for distributed execution on multiple nodes. Their support included code-specific recommendations which addressed  our custom data loading approach.

Their support for multi-node training enabled us to complete benchmarking in a timely manner, which allowed us to apply for the appropriate computing call on schedule.”