4-8 November 2019
Adelaide Convention Centre
Australia/Adelaide timezone

Fast simulation methods in ATLAS: from classical to generative models

4 Nov 2019, 14:15
Riverbank R6 (Adelaide Convention Centre)

Riverbank R6

Adelaide Convention Centre

Oral Track 2 – Offline Computing Track 2 – Offline Computing


Johnny Raine (Universite de Geneve (CH))


The ATLAS physics program relies on very large samples of GEANT4 simulated events, which provide a highly detailed and accurate simulation of the ATLAS detector. However, this accuracy comes with a high price in CPU, and the sensitivity of many physics analyses is already limited by the available Monte Carlo statistics and will be even more so in the future. Therefore, sophisticated fast simulation tools are developed. In Run-3 we aim to replace the calorimeter shower simulation for most samples with a new parametrized description of longitudinal and lateral energy deposits, including machine learning approaches, to achieve a fast and accurate description. Looking further ahead, prototypes are being developed using cutting edge machine learning approaches to learn the appropriate calorimeter response, which are expected to improve modeling of correlations within showers. Two different approaches, using Variational Auto-Encoders (VAEs) or Generative Adversarial Networks (GANs), are trained to model the shower simulation. Additional fast simulation tools will replace the inner detector simulation, as well as digitization and reconstruction algorithms, achieving up to two orders of magnitude improvement in speed. In this talk, we will describe the new tools for fast production of simulated events and an exploratory analysis of the deep learning methods.

Primary authors

Aishik Ghosh (Centre National de la Recherche Scientifique (FR)) Dalila Salamani (Universite de Geneve (CH)) David Rousseau (LAL-Orsay, FR) Gilles Louppe (New York University (US)) Graeme A Stewart (CERN) Hasib Ahmed (The University of Edinburgh (GB)) Heather Gray (LBNL) Jana Schaarschmidt (University of Washington (US)) John Derek Chapman (University of Cambridge (GB)) Johnny Raine (Universite de Geneve (CH)) Kyle Stuart Cranmer (New York University (US)) Stefan Gadatsch (Universite de Geneve (CH)) Tobias Golling (Universite de Geneve (CH)) Tommaso Lari (University and INFN, Milano) Vincent Pascuzzi (University of Toronto (CA))

Presentation Materials