Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics

Article
Report number	arXiv:1912.06794 ; FERMILAB-PUB-20-448-CMS
Title	Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics
Author(s)	Belayneh, Dawit (U. Chicago (main)) ; Carminati, Federico (CERN) ; Farbin, Amir (Texas U., Arlington (main)) ; Hooberman, Benjamin (Illinois U., Urbana (main)) ; Khattak, Gulrukh (CERN ; Unlisted, PK) ; Liu, Miaoyuan (Fermilab) ; Liu, Junze (Illinois U., Urbana (main)) ; Olivito, Dominick (UC, San Diego (main)) ; Barin Pacela, Vitória (U. Helsinki (main)) ; Pierini, Maurizio (CERN) ; Schwing, Alexander (Illinois U., Urbana (main)) ; Spiropulu, Maria (Caltech, Pasadena (main)) ; Vallecorsa, Sofia (CERN) ; Vlimant, Jean-Roch (Caltech, Pasadena (main)) ; Wei, Wei (Illinois U., Urbana (main)) ; Zhang, Matt (Illinois U., Urbana (main))
Publication	2020-07-31
Imprint	2019-12-14
Number of pages	31
Note	26 pages, 38 figures. Corrected typos and added additional references in v2. Extended Acknowledgements section in v3
In:	Eur. Phys. J. C 80 (2020) 688
DOI	10.1140/epjc/s10052-020-8251-9
Subject category	hep-ex ; Particle Physics - Experiment ; cs.LG ; Computing and Computers ; cs.CV ; Computing and Computers ; physics.ins-det ; Detectors and Experimental Techniques
Abstract	Using detailed simulations of calorimeter showers as training data, we investigate the use of deep learning algorithms for the simulation and reconstruction of particles produced in high-energy physics collisions. We train neural networks on shower data at the calorimeter-cell level, and show significant improvements for simulation and reconstruction when using these networks compared to methods which rely on currently-used state-of-the-art algorithms. We define two models: an end-to-end reconstruction network which performs simultaneous particle identification and energy regression of particles when given calorimeter shower data, and a generative network which can provide reasonable modeling of calorimeter showers for different particle types at specified angles and energies. We investigate the optimization of our models with hyperparameter scans. Furthermore, we demonstrate the applicability of the reconstruction model to shower inputs from other detector geometries, specifically ATLAS-like and CMS-like geometries. These networks can serve as fast and computationally light methods for particle shower simulation and reconstruction for current and future experiments at particle colliders.
Copyright/License	preprint: (License: arXiv nonexclusive-distrib 1.0) publication: © The Author(s) 2020 (License: CC-BY-4.0), sponsored by SCOAP³