Noise Filtering Algorithm Based on Graph Neural Network for STCF Drift Chamber

TL;DR

This paper introduces a Graph Neural Network-based noise filtering algorithm to improve charged particle track reconstruction in the high-background environment of the STCF collider, significantly reducing fake rates.

Contribution

The paper presents a novel GNN-based noise filtering method that converts detector data into graphs and applies a tiered threshold strategy for effective background suppression in track reconstruction.

Findings

Reconstruction efficiency remains high with background.

Fake rate is significantly reduced by the GNF Algorithm.

Supports improved track reconstruction in high-background conditions.

Abstract

The super $\tau$-charm facility (STCF) is a next-generation electron-positron collider with high luminosity proposed in China. The higher luminosity leads to increased background level, posing significant challenges for track reconstruction of charged particles. Particularly in the low transverse momentum region, the current track reconstruction algorithm is notably affected by background, resulting in suboptimal reconstruction efficiency and a high fake rate. To address this challenge, we propose a Graph Neural Network (GNN)-based noise filtering algorithm (GNF Algorithm) as a preprocessing step for the track reconstruction. The GNF Algorithm introduces a novel method to convert detector data into graphs and applies a tiered threshold strategy to map GNN-based edge classification results onto signal-noise separation. The study based on Monte Carlo (MC) data shows that with the implementation of the GNF Algorithm, the reconstruction efficiency with the standard background is comparable to the case without background, while the fake rate is significantly reduced. Thus, GNF Algorithm provides essential support for the STCF tracking software.