Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Machine Learning-Based Cluster Classification to Suppress Background in a Prototype RPC Detector

Souvik Chattopadhay, Zubayer Ahammed

Abstract

Resistive Plate Chambers (RPCs) are widely used as tracking detectors in many high-energy physics experiments. It has been observed that low-resistive bakelite RPC prototypes frequently exhibit a secondary hit component, appearing as a long tail or an additional peak in the time-correlation spectra relative to the trigger detector. These secondary hits, which affect both the time and spatial resolution, are difficult to distinguish from genuine signals in high-rate environments without an external trigger. As a result, they can significantly degrade track reconstruction efficiency and increase processing time. We present a machine-learning-based strategy to separate signal and background hit clusters using fifteen cluster-level descriptors that encode both statistical properties (histogram mean, width, cluster size) and fit-based parameters (Gaussian-fit mean, width, amplitude, chi^2, NDF) of the time and ADC distributions. Using laboratory data collected from a single-gap low resistive RPC with a three-scintillator master trigger, we trained and evaluated three classifiers-DNN, 1D-CNN, and XGBoost-on balanced signal/background samples. All models demonstrate strong discrimination capability, with XGBoost showing the most robust generalization performance. Feature-importance analysis indicates that cluster size and temporal-shape descriptors are the dominant discriminants. These results highlight that compact, interpretable cluster-level features combined with machine-learning classifiers offer a practical and effective approach to suppress background in self-triggering low resistive RPC detectors.

Machine Learning-Based Cluster Classification to Suppress Background in a Prototype RPC Detector

Abstract

Resistive Plate Chambers (RPCs) are widely used as tracking detectors in many high-energy physics experiments. It has been observed that low-resistive bakelite RPC prototypes frequently exhibit a secondary hit component, appearing as a long tail or an additional peak in the time-correlation spectra relative to the trigger detector. These secondary hits, which affect both the time and spatial resolution, are difficult to distinguish from genuine signals in high-rate environments without an external trigger. As a result, they can significantly degrade track reconstruction efficiency and increase processing time. We present a machine-learning-based strategy to separate signal and background hit clusters using fifteen cluster-level descriptors that encode both statistical properties (histogram mean, width, cluster size) and fit-based parameters (Gaussian-fit mean, width, amplitude, chi^2, NDF) of the time and ADC distributions. Using laboratory data collected from a single-gap low resistive RPC with a three-scintillator master trigger, we trained and evaluated three classifiers-DNN, 1D-CNN, and XGBoost-on balanced signal/background samples. All models demonstrate strong discrimination capability, with XGBoost showing the most robust generalization performance. Feature-importance analysis indicates that cluster size and temporal-shape descriptors are the dominant discriminants. These results highlight that compact, interpretable cluster-level features combined with machine-learning classifiers offer a practical and effective approach to suppress background in self-triggering low resistive RPC detectors.

Paper Structure

This paper contains 9 sections, 6 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Experimental Setup
  3. Feature Construction
  4. Machine Learning Model
  5. DNN and 1D-CNN model
  6. Boosted Decision Tree (BDT) Model
  7. Performance Evaluation
  8. Summary and Discussion
  9. Acknowledgements

Figures (6)

  • Figure 1: Schematic of the laboratory experimental setup. Three scintillators and one RPC are arranged along the beam axis. Signals from the scintillators are processed by NIM modules (leading-edge discriminators and quad-coincidence logic) to generate the master trigger, while RPC signals are fed to the Front-End Boards (FEBs) and recorded by the DAQ system.
  • Figure 2: Time-correlation plot with respect to master trigger
  • Figure 3: Comparison of signal and background clusters in terms of (a) Cluster-size (b)Intra-cluster time-difference and (c) Intra-cluster ADC-difference distributions.
  • Figure 4: Training history of the baseline DNN model showing accuracy and loss evolution over epochs.
  • Figure 5: Comparison of ROC curves for DNN, CNN, and BDT classifiers.
  • ...and 1 more figures