Issue |
EPJ Web of Conf.
Volume 295, 2024
26th International Conference on Computing in High Energy and Nuclear Physics (CHEP 2023)
|
|
---|---|---|
Article Number | 09010 | |
Number of page(s) | 7 | |
Section | Artificial Intelligence and Machine Learning | |
DOI | https://doi.org/10.1051/epjconf/202429509010 | |
Published online | 06 May 2024 |
https://doi.org/10.1051/epjconf/202429509010
DeepTreeGAN: Fast Generation of High Dimensional Point Clouds
1 Deutsches Elektronen-Synchrotron DESY, Germany
2 Jülich Supercomputing Centre, Institute for Advanced Simulation, Germany
3 RWTH Aachen University, III. Physikalisches Institut A, Germany
4 Universität Hamburg, Institut für Experimentalphysik, Germany
* e-mail: moritz.scham@desy.de
Published online: 6 May 2024
In High Energy Physics, detailed and time-consuming simulations are used for particle interactions with detectors. To bypass these simulations with a generative model, the generation of large point clouds in a short time is required, while the complex dependencies between the particles must be correctly modelled. Particle showers are inherently tree-based processes, as each particle is produced by the decay or detector interaction of a particle of the previous generation. In this work, we present a novel Graph Neural Network model (DeepTreeGAN) that is able to generate such point clouds in a tree-based manner. We show that this model can reproduce complex distributions, and we evaluate its performance on the public JetNet dataset.
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.