A Neural Network for Locating the Primary Vertex in a Pixel Detector

TL;DR

This paper presents a neural network trained on simulated collider data to accurately locate the primary vertex in a pixel detector, outperforming traditional methods in some cases.

Contribution

The study introduces a neural network approach for primary vertex localization that matches or exceeds traditional estimation methods in accuracy.

Findings

Neural network achieves high-precision vertex localization.

Compared neural network with traditional estimates, showing comparable or better performance.

Demonstrates effectiveness using simulated collider data.

Abstract

Using simulated collider data for $p+p\rightarrow 2{\rm Jets}\ $ interactions in a 2-barrel pixel detector, a neural network is trained to construct the coordinate of the primary vertex to a high degree of accuracy. Three other estimates of this coordinate are also considered and compared to that of the neural network. It is shown that the network can match the best of the traditional estimates.