CLAS12 Track Reconstruction with Artificial Intelligence

TL;DR

This paper presents AI-based methods for track reconstruction in the CLAS12 detector, significantly improving efficiency and speed in high luminosity conditions, thereby enhancing data analysis for particle physics experiments.

Contribution

It introduces AI models into track reconstruction software, achieving higher efficiency and faster processing compared to traditional methods.

Findings

Track reconstruction efficiency increased by 10-12% for single particles.

Multi-particle reaction statistics increased by 15-35%.

Tracking speed improved by 35%.

Abstract

In this article we describe the implementation of Artificial Intelligence models in track reconstruction software for the CLAS12 detector at Jefferson Lab. The Artificial Intelligence based approach resulted in improved track reconstruction efficiency in high luminosity experimental conditions. The track reconstruction efficiency increased by $10-12\%$ for single particle, and statistics in multi-particle physics reactions increased by $15\%-35\%$ depending on the number of particles in the reaction. The implementation of artificial intelligence in the workflow also resulted in a speedup of the tracking by $35\%$.