Convolutional Auto-Encoders for Drift Chamber data de-noising for CLAS12

TL;DR

This paper demonstrates that convolutional auto-encoders effectively de-noise drift chamber data, significantly enhancing track reconstruction efficiency at high luminosity, enabling cost savings and improved experimental performance.

Contribution

The study introduces a convolutional auto-encoder based de-noising method that improves track reconstruction efficiency for CLAS12 drift chambers at high luminosity.

Findings

Increased track reconstruction efficiency at high luminosity.

Enables running experiments at twice the luminosity.

Potential for significant operational cost savings.

Abstract

In this article, we present the results of using Convolutional Auto-Encoders for de-noising raw data for CLAS12 drift chambers. The de-noising neural network provides increased efficiency in track reconstruction and also improved performance for high luminosity experimental data collection. The de-noising neural network used in conjunction with the previously developed track classifier neural network \cite{Gavalian:2022hfa} lead to a significant track reconstruction efficiency increase for current luminosity ($0.6\times10^{35}~cm^{-2}~sec^{-1}$ ). The increase in experimentally measured quantities will allow running experiments at twice the luminosity with the same track reconstruction efficiency. This will lead to huge savings in accelerator operational costs, and large savings for Jefferson Lab and collaborating institutions.