Calorimeter shower superresolution
Physical Review D · 14.05.2024 · 109 (9)
DOI: 10.1103/physrevd.109.092009 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physical Review D, online erschienen am 14.05.2024. Verfasst von Ian Pang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 66 Literaturangaben. Gefördert von: U.S. Department of Energy, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung.
Abstract (Originalsprache)
Calorimeter shower simulation is a major bottleneck in the Large Hadron Collider computational pipeline. There have been recent efforts to employ deep-generative surrogate models to overcome this challenge. However, many of best performing models have training and generation times that do not scale well to high-dimensional calorimeter showers. In this work, we introduce SuperCalo, a flow-based superresolution model, and demonstrate that high-dimensional fine-grained calorimeter showers can be quickly upsampled from coarse-grained showers. This novel approach presents a way to reduce computational cost, memory requirements and generation time associated with fast calorimeter simulation models. Additionally, we show that the showers upsampled by SuperCalo possess a high degree of variation. This allows a large number of high-dimensional calorimeter showers to be upsampled from much fewer coarse showers with high-fidelity, which results in additional reduction in generation time.
Förderung
- U.S. Department of Energy
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
Zitieren
APA
Pang, I., Shih, D., & Raine, J. A. (2024). Calorimeter shower superresolution. Physical Review D, 109(9). https://doi.org/10.1103/physrevd.109.092009
Vancouver
Pang I, Shih D, Raine JA. Calorimeter shower superresolution. Physical Review D. 2024;109(9). doi:10.1103/physrevd.109.092009
BibTeX
@article{Pang2024,
author = {Pang, Ian and Shih, David and Raine, John Andrew},
title = {Calorimeter shower superresolution},
journal = {Physical Review D},
year = {2024},
volume = {109},
number = {9},
doi = {10.1103/physrevd.109.092009}
}
EUVIMED