7th Inter-Experimental LHC Machine Learning Workshop

It’s about time: a Point Cloud Generative Model for the CMS High Granularity Calorimeter

Not scheduled

20m

61/1-201 - Pas perdus - Not a meeting room - (CERN)

Poster 3 ML for simulation and surrogate model: Application of ML for simulation or cases of replacing an existing complex model Poster Session

Speaker

William Korcari (Hamburg University (DE))

Description

The High Luminosity LHC upgrade will require corresponding detector upgrades. At CMS, one of the major improvements will be the new high-granularity endcap calorimeters that will have a much higher granularity, with roughly 3 million hexagonal sensors per endcap having different sizes and thicknesses. Moreover, this detector will provide timing information with an average resolution of ~30ps, enabling more efficient track reconstruction and rejection of simultaneous bunch crossings. Fast and accurate simulation of this calorimeter is crucial, but the current simulation techniques based on Geant4 are too slow to provide a sufficient number of events for the foreseen need. Generative machine learning can be leveraged to augment Geant4 simulations and solve this issue. We show the results of a diffusion-based, generative machine learning approach to provide such a simulation, including the timing information.