Auto-encoders for Track Reconstruction in Drift Chambers for CLAS12

TL;DR

This paper presents auto-encoder neural networks that improve track reconstruction in drift chambers for CLAS12 by accurately inferring missing segments, significantly enhancing tracking reliability.

Contribution

The study introduces a novel application of auto-encoders for reconstructing missing track segments in drift chambers, achieving high accuracy and track recovery rates.

Findings

Reconstructed missing segments with approximately 0.35 wire accuracy

Achieved over 99.8% accuracy in recovering missing tracks

Demonstrated effectiveness of neural networks in particle tracking

Abstract

In this article we describe the development of machine learning models to assist the CLAS12 tracking algorithm by identifying tracks through inferring missing segments in the drift chambers. Auto encoders are used to reconstruct missing segments from track trajectory. Implemented neural network was able to reliably reconstruct missing segment positions with accuracy of $\approx 0.35$ wires, and lead to recovery of missing tracks with accuracy of $>99.8\%$.