The particle track reconstruction based on deep learning neural networks

TL;DR

This paper introduces two novel deep learning-based algorithms for particle track reconstruction in high energy physics, improving accuracy and speed over previous methods by integrating preprocessing and classification into a single neural network framework.

Contribution

The paper presents two integrated deep neural network algorithms that eliminate the need for separate preprocessing, enhancing accuracy and computational efficiency in particle track reconstruction.

Findings

Both algorithms outperform previous methods in accuracy.

They are faster and more easily parallelized.

Preliminary results on simulated data are promising.

Abstract

One of the most important problems of data processing in high energy and nuclear physics is the event reconstruction. Its main part is the track reconstruction procedure which consists in looking for all tracks that elementary particles leave when they pass through a detector among a huge number of points, so-called hits, produced when flying particles fire detector coordinate planes. Unfortunately, the tracking is seriously impeded by the famous shortcoming of multiwired, strip in GEM detectors due to the appearance in them a lot of fake hits caused by extra spurious crossings of fired strips. Since the number of those fakes is several orders of magnitude greater than for true hits, one faces with the quite serious difficulty to unravel possible track-candidates via true hits ignoring fakes. On the basis of our previous two-stage approach based on hits preprocessing using directed K-d tree search followed by a deep neural classifier we introduce here two new tracking algorithms. Both algorithms combine those two stages in one while using different types of deep neural nets. We show that both proposed deep networks do not require any special preprocessing stage, are more accurate, faster and can be easier parallelized. Preliminary results of our new approaches for simulated events are presented.