Fast Simulation of Electromagnetic Calorimeter Responses using Deep Learning

Sumitted to PubDB: 2023-05-17

Category: Phd Thesis, Visibility: Public

Tags: -

Authors	Florian Bernlochner, Jubna Irakkathil Jabbar
Non-Belle II authors	Guenter Quast
Date	Jan. 1, 2022
Belle II Number	BELLE2-PTHESIS-2023-010
Abstract	The monte carlo simulations of particle shower responses in electromagnetic calorimeters demand enormous computational resources and time. The area of deep learning and its application to various fields has made significant progress in the past decade. Fast simulation using deep learning can potentially help in reducing the simulation time. The objective of this thesis is to develop a fast simulation of MC particle shower responses in the electromagnetic calorimeter using deep learning models. Generative networks such as the Wasserstein Generative Adversarial Network, Variational Autoencoders, and their combinations are investigated for the studies.
Conference	Karlsruhe