Heidelberg 2022 – wissenschaftliches Programm

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

AKPIK: Arbeitskreis Physik, moderne Informationstechnologie und Künstliche Intelligenz

AKPIK 2: Data Analytics & Machine Learning

AKPIK 2.4: Vortrag

Mittwoch, 23. März 2022, 17:00–17:15, AKPIK-H13

Fast simulation of the HGCAL using generative models — soham bhattacharya¹, samuel bein², engin eren¹, frank gaede¹, gregor kasieczka², •william korcari², dirk kruecker¹, peter mckeown¹, and moritz scham¹ — ¹DESY — ²Universität Hamburg

Accurate simulation of the interaction of particles with the detector materials is of utmost importance for the success of modern particle physics. Software libraries like GEANT4 are tools that already allow the modeling of physical processes inside detectors with high precision. The downside of this method is its computational cost in terms of time. Recent developments in generative machine learning models seem to provide a promising alternative for faster and accurate simulations to accelerate this process. For the challenges of the High Luminosity phase of the LHC, CMS will deploy the High Granularity Calorimeter (HGCal), an imaging calorimeter for the endcap region with a high cell density, and irregular geometry. In this talk, we will show the taken steps in the development of a GraphGAN for the simulation of particle showers in the HGCal and the first achieved results.