Aug 2 – 6, 2021
Europe/Brussels timezone

Detector Reconstruction and Fast Simulation in High-Energy Physics using Graph Generative Models

Aug 6, 2021, 4:00 PM


Parallel contribution H. Statistical Methods for Physics Analysis in the XXI Century Parallels Track H


Mrs Darya Dyachkova (Minerva Schools at KGI)


Accurate and fast simulation of particle physics events is crucial for the high-energy physics community. Simulating particle interactions with the detector is both time consuming and computationally expensive. With its proton-proton collision energy of 13 TeV, the Large Hadron Collider is uniquely positioned to detect and measure the rare phenomena that can shape our knowledge of new interactions. The High-Luminosity Large Hadron Collider (HL-LHC) upgrade will put a significant strain on the computing infrastructure and budget due to increased event rate and levels of pile-up. The simulation of high-energy physics collisions needs to be significantly faster without sacrificing the physics accuracy. Modern machine learning approaches can offer faster solutions, while maintaining a high level of fidelity. We introduce a graph generative model that provides effective reconstruction of LHC events on the level of calorimeter deposits and tracks, paving the way for full detector level fast simulation.

Primary authors

Mr Ali Hariri Mrs Darya Dyachkova (Minerva Schools at KGI) Prof. Sergei Gleyzer (University of Alabama )

Presentation materials

There are no materials yet.