Abstract
The large volume of data expected to be produced by the Belle II experiment presents the opportunity for studies of rare, previously inaccessible processes. Investigating such rare processes in a high data volume environment necessitates a correspondingly high volume of Monte Carlo simulations to prepare analyses and gain a deep understanding of the contributing physics processes to each individual study. This resulting challenge, in terms of computing resource requirements, calls for more intelligent methods of simulation, in particular for processes with very high background rejection rates. This work presents a method of predicting in the early stages of the simulation process the likelihood of relevancy of an individual event to the target study using graph neural networks. The results show a robust training that is integrated natively into the existing Belle II analysis software framework.
Highlights
The Belle II experiment has begun data taking in 2019 [1]
The ultimate goal of this work is integration into the Monte Carlo simulation workflow described in section 2, the key requirement being an overall improvement in the speed of simulating events that reach physics analyses
Graph neural networks exploit the structural information contained in particle decays as well as the properties of the particles themselves
Summary
Over its lifetime it is expected to record an integrated luminosity of 50 ab−1, roughly 50 times that of its predecessor, the Belle experiment [2] Analysing this volume of data requires a correspondingly large volume of simulated data, in particular if the focus is on studies of rare processes (branching ratio < O(10−6)) [3], as is the case at Belle II. This simulated data is used to understand the relevant regions of phase space for a particular study.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
