Physics-aware modelling of an accelerated particle cloud - A&O (Apprentissage et Optimisation) Access content directly
Conference Papers Year : 2023

Physics-aware modelling of an accelerated particle cloud

Abstract

Particle accelerator simulators, pivotal for acceleration optimization, are computationally heavy; surrogate, machine learning-based models are thus trained to facilitate the accelerator fine-tuning. While these current models are efficient, they do not allow for simulating the beam at the individual particle-level. This paper adapts point cloud deep learning methods, developed for computer vision, to model particle beams.
Fichier principal
Vignette du fichier
ML4PS.pdf (729.75 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
licence : Public Domain

Dates and versions

hal-04396175 , version 1 (16-01-2024)

Licence

Attribution

Identifiers

  • HAL Id : hal-04396175 , version 1

Cite

Emmanuel Goutierre, Christelle Bruni, Johanne Cohen, Hayg Guler, Michèle Sebag. Physics-aware modelling of an accelerated particle cloud. MLPS 2023 - Machine Learning and the Physical Sciences Workshop 23023 - At the 37th conference on Neural Information Processing Systems (NeurIPS), Dec 2023, New Orleans, United States. ⟨hal-04396175⟩
67 View
38 Download

Share

Gmail Facebook X LinkedIn More