Heidelberg 2022 – scientific programme

Parts | Days | Selection | Search | Updates | Downloads | Help

T: Fachverband Teilchenphysik

T 53: Data Analysis, Information Technology and Artificial Intelligence 3

T 53.1: Talk

Tuesday, March 22, 2022, 16:15–16:30, T-H38

Improved selective background Monte Carlo simulation at Belle II with graph attention networks and weighted events — •Boyang Yu, Nikolai Hartmann, and Thomas Kuhr — Ludwig-Maximilians-Universität München

When measuring rare processes at Belle II, a huge luminosity is required, which means a large number of simulations are necessary to determine signal efficiencies and background contributions. However, this process demands high computation costs while most of the simulated data, in particular in case of background, are discarded by the event selection. Thus filters using graph neural networks with attention mechanisms are introduced after the Monte Carlo event generation to save the resources for the detector simulation and reconstruction of events discarded at analysis level. Merely filtering out events will however inevitably introduce biases. Therefore statistical methods including sampling and reweighting are invested to deal with this side effect.