Deep Learning Approach to Track Reconstruction in the upgraded VELO

Marco Cristoforetti,K Rinnert

doi:10.1051/epjconf/201921406038

Marco Cristoforetti, K Rinnert

Open Access

https://doi.org/10.1051/epjconf/201921406038

Copy DOI

Abstract

The LHCb experiment will undergo a major upgrade for LHC Run III, scheduled to start taking data in 2021. In order to exploit the full physics potential of the upgraded detector, LHCb will employ a high level event filter entirely implemented in software. The event filter has to operate in real time at the 40 MHz LHC bunch crossing rate. The LHCb collaboration is currently exploring a variety of new new computing paradigms in order to cope with the challenges posed by the high data taking rates. One contribution to this effort is the application of Machine Learning (ML) techniques to particle track reconstruction. We explore an ML approach to the track reconstruction in the upgraded LHCb Vertex Locator (VELO). The reconstruction algorithm is evaluated with fully simulated Minimum-Bias data that reflects the input to the real time event filter. We have achieved a reasonable track reconstruction efficiency and low ghost rate with our first approach and are currently exploring several methods to further quality of the track reconstruction.

Highlights

The LHCb experiment will undergo a major upgrade for LHC Run III, scheduled to start taking data in 2021 [1]
The upgrade of the LHCb detector introduces a radically new datataking strategy: the current multi-level event filter will be replaced by a trigger-less readout system, feeding data into a software event filter at a rate of 40 MHz
The track and vertex reconstruction in the Vertex Locator (VELO) is the first step in the software reconstruction chain

Summary

Introduction

The LHCb experiment will undergo a major upgrade for LHC Run III, scheduled to start taking data in 2021 [1]. The upgrade of the LHCb detector introduces a radically new datataking strategy: the current multi-level event filter will be replaced by a trigger-less readout system, feeding data into a software event filter at a rate of 40 MHz. The entire LHCb tracking system will be replaced by upgraded detector components. The main purpose of the VELO is to provide high-precision primary and decay vertex measurements. The track and vertex reconstruction in the VELO is the first step in the software reconstruction chain. The particle tracks and decay vertices provided by the VELO provide a large fraction of the background suppression power of the software event filter. Full event reconstruction at a rate of 40 MHz is a big challenge, given ever limited computing resources. Recent developments in Machine Learning (ML) and parallel processing enable radically new approaches to event reconstruction.

The LHCb VELO

Track Reconstruction

Results

Conlusions