Speaker
Arne Christoph Reimers
(CERN)
Description
Development, characterization, and integration of ML models to reject common-mode noise in the CMS HGCAL for the HL-LHC.
CERN group/ Experiment
EP-CMG
| Working area | Area 2: Optimal AI deployment for Online Data Processing |
|---|---|
| Project goals | Deployment of an optimized ML model to reject common-mode noise in online HGCAL operation |
| Timeline | Characterization of noise and development of models on test beam data and simulation in 2025-26. Integration in CMS software for HGCal reconstruction in 2026. Full integration in software and firmware for HGCal data-taking before start of Run 4 |
| Available person power | 30% of research fellow + staff supervision |
| Additional person power request | None |
| Is this an already ongoing activity? | Yes |
| Indicative hardware resources needs | Access to a GPU cluster with LCG-like software stack and cvmfs access with fast storage facilities across the full duration of the project |
Authors
André David
(CERN)
Arne Christoph Reimers
(CERN)
Izaak Neutelings
(CERN (CH))
Josh Bendavid
(CERN)
Kyle Cormier
(CERN)
Pedro Vieira De Castro Ferreira Da Silva
(CERN)