Refining Fast Simulation Using Machine Learning

Conference · Tue Oct 29 00:00:00 EDT 2024

DOI:https://doi.org/10.2172/2477010· OSTI ID:2477010

Güngördü, Acelya Deniz ^[1]; Boncukcu, Dorukhan ^[1]; Pedro, Kevin ^[2]; Bein, Samuel Louis ^[3]; Wolf, Moritz Jonas ^[4]; Vural, Mirac Ekim ^[1]; Cakir, Altan ^[1]

---

1. Istanbul, Tech. U.
2. Fermilab
3. Louvain U., CP3
4. Hamburg U.

A growing reliance on the fast Monte Carlo (FastSim) will accompany the high luminosity and detector granularity expected in Phase 2. FastSim is roughly 10 times faster than equivalent GEANT4-based full simulation (FullSim). However, reduced accuracy of the FastSim affects some analysis variables and collections. To improve its accuracy, FastSim is refined using regression-based neural networks trained with ML. The status of FastSim refinement is presented. The results show improved agreement with the FullSim output and an improvement in correlations among output observables and external parameters.

• Research Organization: Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)
• Sponsoring Organization: USDOE Office of Science (SC), High Energy Physics (HEP) (SC-25)
• Contributing Organization: CMS
• DOE Contract Number: AC02-07CH11359
• OSTI ID: 2477010
• Report Number(s): FERMILAB-POSTER-24-0302-CMS-CSAID-PPD; oai:inspirehep.net:2843437
• Country of Publication: United States
• Language: English