A neural network z-vertex trigger for Belle II

16th International workshop on Advanced Computing and Analysis Techniques in physics research

物理学;计算机科学

Neuhaus, S.^1 ; Skambraks, S.^2 ; Abudinen, F.^3 ; Chen, Y.^1 ; Feindt, M.^4 ; Frühwirth, R.^5 ; Heck, M.^4 ; Kiesling, C.^3 ; Knoll, A.^1 ; Paul, S.^2 ; Schieck, J.^5

Institute for Robotics and Embedded Systems, Technische Universität München, Germany^1

Physik Department, Technische Universität München, Germany^2

Max-Planck-Institut für Physik, München, Germany^3

Institute for Experimental Nuclear Physics, Karlsruher Institut für Technologie, Germany^4

Institute for High Energy Physics, Österreichische Akademie der Wissenschaften, Austria^5

关键词: Azimuthal angle;    Central drift chambers;    Input values;    Interaction region;    Stereo wires;    Track reconstruction;    Track trigger;    Transverse momenta;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/608/1/012052/pdf
DOI  :  10.1088/1742-6596/608/1/012052

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

We present the concept of a track trigger for the Belle II experiment, based on a neural network approach, that is able to reconstruct the z (longitudinal) position of the event vertex within the latency of the first level trigger. The trigger will thus be able to suppress a large fraction of the dominating background from events outside of the interaction region. The trigger uses the drift time information of the hits from the Central Drift Chamber (CDC) of Belle II within narrow cones in polar and azimuthal angle as well as in transverse momentum (sectors), and estimates the z-vertex without explicit track reconstruction. The preprocessing for the track trigger is based on the track information provided by the standard CDC trigger. It takes input from the 2D (r - φ) track finder, adds information from the stereo wires of the CDC, and finds the appropriate sectors in the CDC for each track in a given event. Within each sector, the z-vertex of the associated track is estimated by a specialized neural network, with a continuous output corresponding to the scaled z-vertex. The input values for the neural network are calculated from the wire hits of the CDC.