Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Benchmarking Quantum Convolutional Neural Networks for Signal Classification in Simulated Gamma-Ray Burst Detection

Farida Farsian, Nicolò Parmiggiani, Alessandro Rizzo, Gabriele Panebianco, Andrea Bulgarelli, Francesco Schillirò, Carlo Burigana, Vincenzo Cardone, Luca Cappelli, Massimo Meneghetti, Giuseppe Murante, Giuseppe Sarracino, Roberto Scaramella, Vincenzo Testa, Tiziana Trombetti

TL;DR

The paper investigates the use of Quantum Convolutional Neural Networks (QCNNs) to detect Gamma-Ray Burst (GRB)-like signals in simulated Cherenkov Telescope Array Observatory data. It compares QCNNs to a minimal classical CNN using a hybrid quantum-classical pipeline implemented in Qiskit, across data encoding methods and qubit counts. Key findings show QCNNs can reach about 97.5% test accuracy with fewer parameters than the classical model, with data re-uploading generally outperforming amplitude encoding and higher qubit counts enhancing performance at the cost of training time. The study also demonstrates QCNNs' strong generalization under limited training data and confirms reasonable performance on real AGILE data, highlighting potential hardware-aware benefits and guiding future quantum-enabled astrophysical data analysis.

Abstract

This study evaluates the use of Quantum Convolutional Neural Networks (QCNNs) for identifying signals resembling Gamma-Ray Bursts (GRBs) within simulated astrophysical datasets in the form of light curves. The task addressed here focuses on distinguishing GRB-like signals from background noise in simulated Cherenkov Telescope Array Observatory (CTAO) data, the next-generation astrophysical observatory for very high-energy gamma-ray science. QCNNs, a quantum counterpart of classical Convolutional Neural Networks (CNNs), leverage quantum principles to process and analyze high-dimensional data efficiently. We implemented a hybrid quantum-classical machine learning technique using the Qiskit framework, with the QCNNs trained on a quantum simulator. Several QCNN architectures were tested, employing different encoding methods such as Data Reuploading and Amplitude encoding. Key findings include that QCNNs achieved accuracy comparable to classical CNNs, often surpassing 90\%, while using fewer parameters, potentially leading to more efficient models in terms of computational resources. A benchmark study further examined how hyperparameters like the number of qubits and encoding methods affected performance, with more qubits and advanced encoding methods generally enhancing accuracy but increasing complexity. QCNNs showed robust performance on time-series datasets, successfully detecting GRB signals with high precision. The research is a pioneering effort in applying QCNNs to astrophysics, offering insights into their potential and limitations. This work sets the stage for future investigations to fully realize the advantages of QCNNs in astrophysical data analysis.

Benchmarking Quantum Convolutional Neural Networks for Signal Classification in Simulated Gamma-Ray Burst Detection

TL;DR

The paper investigates the use of Quantum Convolutional Neural Networks (QCNNs) to detect Gamma-Ray Burst (GRB)-like signals in simulated Cherenkov Telescope Array Observatory data. It compares QCNNs to a minimal classical CNN using a hybrid quantum-classical pipeline implemented in Qiskit, across data encoding methods and qubit counts. Key findings show QCNNs can reach about 97.5% test accuracy with fewer parameters than the classical model, with data re-uploading generally outperforming amplitude encoding and higher qubit counts enhancing performance at the cost of training time. The study also demonstrates QCNNs' strong generalization under limited training data and confirms reasonable performance on real AGILE data, highlighting potential hardware-aware benefits and guiding future quantum-enabled astrophysical data analysis.

Abstract

This study evaluates the use of Quantum Convolutional Neural Networks (QCNNs) for identifying signals resembling Gamma-Ray Bursts (GRBs) within simulated astrophysical datasets in the form of light curves. The task addressed here focuses on distinguishing GRB-like signals from background noise in simulated Cherenkov Telescope Array Observatory (CTAO) data, the next-generation astrophysical observatory for very high-energy gamma-ray science. QCNNs, a quantum counterpart of classical Convolutional Neural Networks (CNNs), leverage quantum principles to process and analyze high-dimensional data efficiently. We implemented a hybrid quantum-classical machine learning technique using the Qiskit framework, with the QCNNs trained on a quantum simulator. Several QCNN architectures were tested, employing different encoding methods such as Data Reuploading and Amplitude encoding. Key findings include that QCNNs achieved accuracy comparable to classical CNNs, often surpassing 90\%, while using fewer parameters, potentially leading to more efficient models in terms of computational resources. A benchmark study further examined how hyperparameters like the number of qubits and encoding methods affected performance, with more qubits and advanced encoding methods generally enhancing accuracy but increasing complexity. QCNNs showed robust performance on time-series datasets, successfully detecting GRB signals with high precision. The research is a pioneering effort in applying QCNNs to astrophysics, offering insights into their potential and limitations. This work sets the stage for future investigations to fully realize the advantages of QCNNs in astrophysical data analysis.

Paper Structure

This paper contains 18 sections, 2 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Quantum Machine Learning
  3. Variational Quantum Algorithm
  4. Data Encoding methods
  5. Dataset
  6. The simulation specification
  7. Architecture
  8. Quantum Convolutional Neural Network
  9. Classical CNN
  10. Benchmarking parameters
  11. Training
  12. Results
  13. The General Trend
  14. The Qubit number effect
  15. The data encoding effect
  16. ...and 3 more sections

Figures (3)

  • Figure 1: A sample of Simulated Light curves used in training and test set. Y axis show the photon count while the x axis is the time. Blue curve shows the GRB signal with underlying background while orange shows only the background noise. This curve was sampled with bin=10s
  • Figure 2: Example of the used quantum circuit in QCNN architecture with 5 qubits, the purple with "R" shows the rotation gates while the blue and "+" sign are CNOT gates demonstration the entanglement operation.
  • Figure 3: Objectuve function value against iteration during the training the QCNN