ACAT 2021

Tracking with object condensation

contribution ID 720

Not scheduled

20m

Auditorium (Virtual and IBS Science Culture Center, Daejeon, South Korea)

Oral Track 2: Data Analysis - Algorithms and Tools Track 2: Data Analysis - Algorithms and Tools

Speakers

Mary Touranakou (National and Kapodistrian University of Athens (GR)) Shah Rukh Qasim (Manchester Metropolitan University (GB))

Description

We investigate the application of object condensation to particle tracking at the LHC. Designed having in mind calorimeter clustering and successfully employed on high-granularity calorimeter reconstruction for HL-LHC, object condensation is a generic clustering methods that could be applied to many problems within and outside HEP. Using the TrackML challenge dataset, we train a tracking algorithm based on object condensation and present results for events of increasing complexity.

References

https://arxiv.org/abs/2002.03605
https://arxiv.org/abs/2106.01832

Significance

Being entirely based on a differentiable algorithm, tracking based on this algorithm could come with advantages in terms of speed up and resource exploitation of parallel architectures that could become the standard by HL-LHC