Aachen 2019 – scientific programme

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

AKPIK: Arbeitskreis Physik, moderne Informationstechnologie und Künstliche Intelligenz

AKPIK 2: Machine-learning methods and computing in particle physics

AKPIK 2.1: Talk

Tuesday, March 26, 2019, 16:00–16:10, H10

Pixel detector background simulation using generative adversarial networks at Belle II — •Matej Srebre — Ludwig-Maximilians-Universität München

The Pixel Vertex Detector (PXD) is an essential part of the Belle II experiment, allowing us to determinate the location of particle trajectories and decay vertices. The combined data from multiple detector subsystems along with PXD information is crucial in the event reconstruction phase to determine particle types, their tracks, and the decay chain. To model the effect of unwanted background noise on the track reconstruction in simulation we add simulated or recorded background data to the simulated detector signals from the generated physics process of interest. A large batch of statistically independent samples of background noise is required to not be biased by statistical fluctuations in the background data. The data from the PXD, however, is high in volume and requires a substantial amount of storage and bandwidth. As an efficient way of producing background noise we explore the idea of an on-demand noise generator using Generative Adversarial Networks.