EUVIMEDOpdag EUVIMED
Crossref

Denoising diffusion models with geometry adaptation for high fidelity calorimeter simulation

Oz Amram, Kevin Pedro

Physical Review D · 2023-10-27 · 108 (7)

DOI: 10.1103/physrevd.108.072014 ↗

At a glance

Journal article in Physical Review D, published online on 2023-10-27. Written by Oz Amram and 1 co-authors. Cited 43 times so far (Crossref); 35 references. Funded by: Fermilab, U.S. Department of Energy, Office of Science.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Simulation is crucial for all aspects of collider data analysis, but the available computing budget in the High Luminosity LHC era will be severely constrained. Generative machine learning models may act as surrogates to replace physics-based full simulation of particle detectors, and diffusion models have recently emerged as the state of the art for other generative tasks. We introduce CaloDiffusion, a denoising diffusion model trained on the public CaloChallenge datasets to generate calorimeter showers. Our algorithm employs 3D cylindrical convolutions, which take advantage of symmetries of the underlying data representation. To handle irregular detector geometries, we augment the diffusion model with a new geometry latent mapping (GLaM) layer to learn forward and reverse transformations to a regular geometry that is suitable for cylindrical convolutions. The showers generated by our approach are nearly indistinguishable from the full simulation, as measured by several different metrics.

Funding

  • Fermilab
  • U.S. Department of Energy
  • Office of Science
  • High Energy Physics

Cite

APA

Amram, O., & Pedro, K. (2023). Denoising diffusion models with geometry adaptation for high fidelity calorimeter simulation. Physical Review D, 108(7). https://doi.org/10.1103/physrevd.108.072014

Vancouver

Amram O, Pedro K. Denoising diffusion models with geometry adaptation for high fidelity calorimeter simulation. Physical Review D. 2023;108(7). doi:10.1103/physrevd.108.072014

BibTeX
@article{Amram2023,
  author = {Amram, Oz and Pedro, Kevin},
  title = {Denoising diffusion models with geometry adaptation for high fidelity calorimeter simulation},
  journal = {Physical Review D},
  year = {2023},
  volume = {108},
  number = {7},
  doi = {10.1103/physrevd.108.072014}
}
Start for free →