Project Goal

CERN leads Work Package 4 (WP4) which aims at the development and expansion of AI methods along representative use-cases from research and industry, which have a strong focus on data-driven technologies, i.e., analyzing data-rich descriptions of physical phenomena. The outcomes are applicable to intelligent workflows including innovative AI methods and techniques, optimized on HPC-to-Exascale systems. The tasks contain the capabilities to evaluate prototype algorithms based on experimental and/or simulation data, code performance on Exascale HPC systems, and quality of data models.

Background

WP4 contains four tasks: Event reconstruction and classification at the CERN HL-LHC, led by CERN; Seismic imaging with remote sensing for energy applications, led by CYI; Defect-free additive manufacturing, led by FM; Sound Engineering, led by UOI.

Task 4.1 develops a GPU native and AI-based algorithm for particle-flow reconstruction that can easily be accelerated by modern heterogeneous hardware. This algorithm, called Machine-Learned Particle-Flow (MLPF), is developed in collaboration with CMS and acts as a representative AI use case from HEP. Some of the most important contributions from T4.1 include the implementation and execution of distributed training and large-scale hyperparameter optimization using HPC, significantly improving physics performance. Another area of work has been to optimize developed algorithms on various heterogenous architectures.

Progress in 2024

In T4.1, the MLPF (Machine-Learned Particle Flow) studies on the open electron-positron collision dataset has been completed and focus has shifted back to simulated CMS-based datasets with proton-proton collisions. A strategic decision was made to migrate the optimization code of MLPF from TensorFlow to PyTorch. The reason for this is the superior support for cutting edge tools offered by PyTorch as well as its suitability for easy and fast development of new algorithms. The work started in 2023 and has now been completed. To further test the exascale potential of AI workloads like MLPF, a study on the neural scaling laws of MLPF was carried out using the new PyTorch version of the model and training code. This study was presented at the PASC24 conference in Zurich, Switzerland.

The CoE RAISE project came to an end in July of 2024 and the final EC review was carried out in September. The project received nothing but good feedback from the reviewers, who congratulated all project partners and praised the project outcomes.

Next Steps

CoE RAISE concluded its activities at the end of July 2024. Following this, the MLPF group will continue its work on AI-based particle flow reconstruction. However, this ongoing effort will experience a reduction in support from CERN openlab due to the cessation of funding associated with CoE RAISE.

Project Coordinator: Maria Girone, Andreas Lintermann

Technical Team: Maria Girone, David Southwick, Eric Wulff

Collaboration Liaisons: Marcel Aach (Forschungszentrum Jülich), Naveed Akram (The Cyprus Institute), Gabriele Cavallaro (Forschungszentrum Jülich), Kurt de Grave (Flanders Make), Andreas Lintermann (Forschungszentrum Jülich), Arnis Lektauers (Riga Technical University), Morris Riedel (University of Iceland), Nikos Savva (The Cyprus Institute), Eric Michael Sumner (University of Iceland), Liang Tian (University of Iceland), Eric Verschuur (Delft University of Technology)

In partnership with: CoE RAISE (EC funded), discover more on coe-raise.eu