The Neural Network First-Level Hardware Track Trigger of the Belle II Experiment

by Prof. Christian Kiesling (MPP)

Thursday 23 Jan 2025, 09:30 → 10:30 Europe/Berlin

E18/ENE Seminar Room 3268 (TUM PH)

We describe the principles and performance of the first-level ("L1'') hardware track trigger of Belle II, which is based on neural networks. The inputs to the networks are derived from Belle II's central drift chamber (CDC) which is equipped with alternating axial and stereo wire planes. Track finding is done with Hough transforms using the axial wire planes of the CDC, yielding 2D track candidates. Further pre-processing selects the suitable information from the stereo planes and prepares the input for the neural networks, which then provide estimates for the origin of the track candidates in direction of the colliding beams ("$z$-vertex''), as well as their polar emission angles $\theta$. Using a cut $d$ on the $z$-vertices of the "neural'' tracks allows us to identify events coming from the collision region ($z \approx 0$), and to suppress the overwhelming background from outside. Requiring $|z| < d$ for at least one neural track in an event with two or more 2D candidates will set an L1 track trigger. The networks also enable a minimum bias trigger, requiring a single 2D track candidate validated by a neural track with a momentum larger than 0.7 GeV in addition to the $|z|$ condition. The neural trigger is operating since the year 2020 as the main track trigger of Belle II.  We also sketch our concepts for upgrading the neural trigger in view of rising instantaneous luminosities and increasing backgrounds, and describe our plans for triggering new, feebly interacting neutral particles, decaying into charged pairs far from the interaction region.