Simultaneous energy and mass calibration of large-radius jets with the ATLAS detector using a deep neural network

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68378271%3A_____%2F24%3A00598476" target="_blank" >RIV/68378271:_____/24:00598476 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21220/24:00377475 RIV/68407700:21240/24:00377475 RIV/68407700:21340/24:00377475 RIV/68407700:21670/24:00377475 a 2 dalších

Výsledek na webu

<a href="https://hdl.handle.net/11104/0356144" target="_blank" >https://hdl.handle.net/11104/0356144</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1088/2632-2153/ad611e" target="_blank" >10.1088/2632-2153/ad611e</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Simultaneous energy and mass calibration of large-radius jets with the ATLAS detector using a deep neural network

Popis výsledku v původním jazyce

The energy and mass measurements of jets are crucial tasks for the Large Hadron Collider experiments. This paper presents a new calibration method to simultaneously calibrate these quantities for large-radius jets measured with the ATLAS detector using a deep neural network (DNN). To address the specificities of the calibration problem, special loss functions and training procedures are employed, and a complex network architecture, which includes feature annotation and residual connection layers, is used. The DNN-based calibration is compared to the standard numerical approach in an extensive series of tests. The DNN approach is found to perform significantly better in almost all of the tests and over most of the relevant kinematic phase space. In particular, it consistently improves the energy and mass resolutions, with a 30% better energy resolution obtained for transverse momenta pT>500pT​>500 GeV.

Název v anglickém jazyce

Simultaneous energy and mass calibration of large-radius jets with the ATLAS detector using a deep neural network

Popis výsledku anglicky

The energy and mass measurements of jets are crucial tasks for the Large Hadron Collider experiments. This paper presents a new calibration method to simultaneously calibrate these quantities for large-radius jets measured with the ATLAS detector using a deep neural network (DNN). To address the specificities of the calibration problem, special loss functions and training procedures are employed, and a complex network architecture, which includes feature annotation and residual connection layers, is used. The DNN-based calibration is compared to the standard numerical approach in an extensive series of tests. The DNN approach is found to perform significantly better in almost all of the tests and over most of the relevant kinematic phase space. In particular, it consistently improves the energy and mass resolutions, with a 30% better energy resolution obtained for transverse momenta pT>500pT​>500 GeV.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10303 - Particles and field physics

Projekt

<a href="/cs/project/EH22_008%2F0004632" target="_blank" >EH22_008/0004632: Výzkum základních stavebních kamenů hmoty s využitím špičkových technologií</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Machine Learning-Science and Technology

ISSN

2632-2153

e-ISSN

2632-2153

Svazek periodika

5

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

37

Strana od-do

035051

Kód UT WoS článku

001394493600001

EID výsledku v databázi Scopus

2-s2.0-85203423356