Speakers
Description
Run-3 and HL-LHC analyses require billions of events and numerous systematic variations, making full Geant4 simulation prohibitively slow; a calorimeter fast-simulation offers ~10× speed-up but remains less accurate for hadronic showers, particularly for sub-showers displaced from the shower axis. This project builds on advances from industry-scale image generative AI (e.g., diffusion and transformer models) to raise hadronic-shower accuracy for current ATLAS calorimetry and forthcoming high-granularity designs, while explicitly accounting for memory constraints inherent to large-scale HEP production.
Planned developments include optimised voxelisation alongside point-cloud generative models that preserve fine granularity and are engineered for high throughput in HEP workflows; conditioning on local geometry and materials to handle complex regions (cracks, boundaries); and uncertainty-aware, data-driven tuning that conditions models directly on LHC data within its quoted uncertainties. A rigorous comparison programme against Geant4 and collision data, together with ML-based validation/diff tools, will localise discrepancies across fast-sim variants and document improvements in shower shapes, response, and resolution—at fast-simulation speed.
CERN group/ Experiment
CERN ATLAS Team
| Working area | Area 7: Experimental Technologies |
|---|---|
| Project goals | High quality fast simulation of calorimeter suitable to replace Geant4 for all Monte Carlo needs for the ATLAS calorimeter and future high granular calorimeter designs |
| Timeline | Year 1 : develop sufficiently expressive AI models for hadronic shower substructure based on ATLAS calorimeter granularity needs Year 2 : implementation of hadronic shower model in ATLAS and validation against Geant4 + further development of AI model for future high granular calorimeters Year 3 : training and tuning of hadronic shower model against ATLAS data |
| Available person power | 0.7 FTE |
| Additional person power request | 36 GRAP months |
| Is this an already ongoing activity? | Yes |
| Indicative hardware resources needs | Hardware: current GPU training resources through CERN IT sufficient as long as they stay available at current occupation |