Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2112.02655

Quantum Machine Learning for Radio Astronomy

Mohammad Kordzanganeh, Aydin Utting, Anna M. M. Scaife

Published Dec 5, 2021• 9 citations
arXivHTMLPDF

Abstract

In this work we introduce a novel approach to the pulsar classification problem in time-domain radio astronomy using a Born machine, often referred to as a quantum neural network. Using a single-qubit architecture, we show that the pulsar classification problem maps well to the Bloch sphere and that comparable accuracies to more classical machine learning approaches are achievable. We introduce a novel single-qubit encoding for the pulsar data used in this work and show that this performs comparably to a multi-qubit QAOA encoding.

DOI
10.48550/arxiv.2112.02655

Related papers

Optimising Pulsar Classification in Astronomy through Quantum-Assisted Approach

Vaidehi Gawande, Jayesh V. Hire, Sagar Dhande

Abstract Pulsar stars, characterized by their highly magnetized and rapidly rotating compact nature, as well as their emission of radiation beams from magnetic poles, play a crucial role in astrophysics, particularly in the study of gravitational waves and general relativity. This paper investigates the application of machine learning techniques for the classification of pulsars using radio wave emission data from the HTRU-2 dataset, which contains an extensive collection of candidate samples. The study explores two quantum-assisted methodologies: a multi-qubit Quantum Approximate Optimization Algorithm (QAOA) inspired encoding and an innovative single-qubit Quantum Asymptotically Universal Multi-feature (QAUM) encoding within a quantum neural network framework. The performance evaluation encompasses a range of metrics, including accuracy, precision, recall, and specificity, which are analyzed across various optimizer configurations and learning rates. Notably, the QAUM approach consistently demonstrates superior sensitivity and reduced error rates compared to QAOA, particularly evident at specific learning rate settings. These findings underscore the transformative potential of quantum computing in advancing pulsar detection methodologies, highlighting its efficacy and implications for astrophysical data analysis and the broader field of quantum-enhanced scientific exploration.

•Jul 15, 2025•0 citations

Qiskit Variational Quantum Classifier on the Pulsar Classification Problem

Souza, Anna B. M., Clebson Cruz, Marcelo Albano Moret

Quantum Machine Learning is a new computational tool that combines the quantum properties from quantum computing with the pattern recognition from machine learning. In this paper, we apply the Variational Quantum Classifier algorithm to the problem of pulsar classification of candidates from the High Time Resolution Universe 2 dataset. We use Qiskit Machine Learning circuits to compare the performance of the model using different feature selection methods, various number of features and training data size. Comparisons on the model from changing the data encoding and ansatz options are also reported. Keywords: Quantum Computing, Quantum Machine Learning, Astrophysics, Pulsars

arXiv:2505.15600•May 21, 2025•0 citations

Pulsar classification: comparing quantum convolutional neural networks and quantum support vector machines

Donovan Slabbert, Matt Lourens, Francesco Petruccione

Abstract Well-known quantum machine learning techniques, specifically quantum kernel-assisted support vector machines (QSVMs) and quantum convolutional neural networks (QCNNs), are applied to the binary classification of pulsars. In this comparative study, it is illustrated with simulations that both quantum methods successfully achieve effective classification of the HTRU-2 data set that connects pulsar class labels to eight separate features. While QCNNs are superior in terms of training and prediction speed compared to QSVMs, the preference shifts toward QSVMs when the present noisy NISQ-era devices are incorporated into the comparison. QSVMs demonstrate superior overall performance compared to QCNNs when assessed using binary classification performance metrics. Classical methods are implemented to serve as a benchmark for comparison with the quantum approaches.

arXiv:2309.15592•Quantum Machine Intelligence•Sep 6, 2024•11 citations

The Variational Quantum Classifier from Qiskit Machine Learning Applied to the Classification of Pulsar Stars

Anna B. M. Souza, Clebson Cruz, Marcelo Albano Moret +1 more

Quantum Machine Learning is a new computational tool that combines the quantum properties from quantum computing with the pattern recognition from machine learning. In this paper, we apply the Variational Quantum Classifier algorithm to the problem of pulsar classification of candidates from the High Time Resolution Universe 2 dataset. We use Qiskit Machine Learning circuits to compare the performance of the model using different feature selection methods, various number of features and training data size. Comparisons on the model from changing the data encoding and ansatz options are also reported.

IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON)•Oct 28, 2025•1 citation

Quantum Machine Learning for Identifying Fast Radio Bursts

Agastya Kapur

Since their discovery in 2007, fast radio bursts (FRBs) have become a major focus of radio astronomy research because they enable researchers to probe the intergalactic medium beyond the Milky Way. Finding more FRBs will enable better understanding of the local and distant universe and the physics that drives these violent ultra-luminous events. Even though various classical machine learning algorithms have been used to search for FRBs, here I show, for the first time, that quantum machine learning algorithms can be used for detecting FRBs in large datasets. Quantum machine learning algorithms are still in their infancy, but show potential to outperform classical machine learning methods. I investigate how effective quantum machine learning, specifically the quantum convolutional neural network (QCNN), can be for identifying FRBs in radio astronomy datasets. The QCNNs developed for this work use 8, 10 and 12 qubits. These models can be run on existing quantum hardware; however, I run classical simulations to test the quantum models in a noise-free environment. Using a new FRB training dataset created for this work, QCNNs were trained, and their performance was evaluated by comparing them to classical machine learning models: the random forest and convolutional neural network. I demonstrate that the best quantum model outperforms the classical models tested. It was observed that performance improved with increasing numbers of qubits. The best QCNN model developed for this work was also applied to real data from the CSIRO Parkes radio telescope Murriyang and was successfully used to find a radio burst from a real astronomical source. This work demonstrates that QCNNs can detect FRBs in real astronomy datasets.

•Apr 1, 2026•0 citations

Classical ensembles of single-qubit quantum variational circuits for classification

Shane McFarthing, Anban W. Pillay, Ilya Sinayskiy +1 more

Abstract The quantum asymptotically universal multi-feature (QAUM) encoding architecture was recently introduced and showed improved expressivity and performance in classifying pulsar stars. The circuit uses generalized trainable layers of parameterized single-qubit rotation gates and single-qubit feature encoding gates. Although the improvement in classification accuracy is promising, the single-qubit nature of this architecture, combined with the circuit depth required for accuracy, limits its applications on NISQ devices due to their low coherence times. This work reports on the design, implementation, and evaluation of ensembles of single-qubit QAUM classifiers using classical bagging and boosting techniques. We demonstrate an improvement in validation accuracy for pulsar star classification. We find that this improvement is not dataset specific as we observe consistent improvements for the MNIST Digits and Wisconsin Cancer datasets. We also observe that the boosting ensemble achieves an acceptable level of accuracy with only a small amount of training, while the bagging ensemble achieves higher overall accuracy with ample training time. This shows that classical ensembles of single-qubit circuits present a new approach for certain classification problems.

arXiv:2302.02964•Quantum Machine Intelligence•Nov 16, 2024•6 citations
In this work we introduce a novel approach to the pulsar classification problem in time-domain radio astronomy using a Born machine, often referred to as a quantum neural network. Using a single-qubit architecture, we show that the pulsar classification problem maps well to the Bloch sphere and that comparable accuracies to more classical machine learning approaches are achievable. We introduce a novel single-qubit encoding for the pulsar data used in this work and show that this performs comparably to a multi-qubit QAOA encoding.
Abstract Pulsar stars, characterized by their highly magnetized and rapidly rotating compact nature, as well as their emission of radiation beams from magnetic poles, play a crucial role in astrophysics, particularly in the study of gravitational waves and general relativity. This paper investigates the application of machine learning techniques for the classification of pulsars using radio wave emission data from the HTRU-2 dataset, which contains an extensive collection of candidate samples. The study explores two quantum-assisted methodologies: a multi-qubit Quantum Approximate Optimization Algorithm (QAOA) inspired encoding and an innovative single-qubit Quantum Asymptotically Universal Multi-feature (QAUM) encoding within a quantum neural network framework. The performance evaluation encompasses a range of metrics, including accuracy, precision, recall, and specificity, which are analyzed across various optimizer configurations and learning rates. Notably, the QAUM approach consistently demonstrates superior sensitivity and reduced error rates compared to QAOA, particularly evident at specific learning rate settings. These findings underscore the transformative potential of quantum computing in advancing pulsar detection methodologies, highlighting its efficacy and implications for astrophysical data analysis and the broader field of quantum-enhanced scientific exploration.
Quantum Machine Learning is a new computational tool that combines the quantum properties from quantum computing with the pattern recognition from machine learning. In this paper, we apply the Variational Quantum Classifier algorithm to the problem of pulsar classification of candidates from the High Time Resolution Universe 2 dataset. We use Qiskit Machine Learning circuits to compare the performance of the model using different feature selection methods, various number of features and training data size. Comparisons on the model from changing the data encoding and ansatz options are also reported. Keywords: Quantum Computing, Quantum Machine Learning, Astrophysics, Pulsars
Abstract Well-known quantum machine learning techniques, specifically quantum kernel-assisted support vector machines (QSVMs) and quantum convolutional neural networks (QCNNs), are applied to the binary classification of pulsars. In this comparative study, it is illustrated with simulations that both quantum methods successfully achieve effective classification of the HTRU-2 data set that connects pulsar class labels to eight separate features. While QCNNs are superior in terms of training and prediction speed compared to QSVMs, the preference shifts toward QSVMs when the present noisy NISQ-era devices are incorporated into the comparison. QSVMs demonstrate superior overall performance compared to QCNNs when assessed using binary classification performance metrics. Classical methods are implemented to serve as a benchmark for comparison with the quantum approaches.
Quantum Machine Learning is a new computational tool that combines the quantum properties from quantum computing with the pattern recognition from machine learning. In this paper, we apply the Variational Quantum Classifier algorithm to the problem of pulsar classification of candidates from the High Time Resolution Universe 2 dataset. We use Qiskit Machine Learning circuits to compare the performance of the model using different feature selection methods, various number of features and training data size. Comparisons on the model from changing the data encoding and ansatz options are also reported.
Since their discovery in 2007, fast radio bursts (FRBs) have become a major focus of radio astronomy research because they enable researchers to probe the intergalactic medium beyond the Milky Way. Finding more FRBs will enable better understanding of the local and distant universe and the physics that drives these violent ultra-luminous events. Even though various classical machine learning algorithms have been used to search for FRBs, here I show, for the first time, that quantum machine learning algorithms can be used for detecting FRBs in large datasets. Quantum machine learning algorithms are still in their infancy, but show potential to outperform classical machine learning methods. I investigate how effective quantum machine learning, specifically the quantum convolutional neural network (QCNN), can be for identifying FRBs in radio astronomy datasets. The QCNNs developed for this work use 8, 10 and 12 qubits. These models can be run on existing quantum hardware; however, I run classical simulations to test the quantum models in a noise-free environment. Using a new FRB training dataset created for this work, QCNNs were trained, and their performance was evaluated by comparing them to classical machine learning models: the random forest and convolutional neural network. I demonstrate that the best quantum model outperforms the classical models tested. It was observed that performance improved with increasing numbers of qubits. The best QCNN model developed for this work was also applied to real data from the CSIRO Parkes radio telescope Murriyang and was successfully used to find a radio burst from a real astronomical source. This work demonstrates that QCNNs can detect FRBs in real astronomy datasets.
Abstract The quantum asymptotically universal multi-feature (QAUM) encoding architecture was recently introduced and showed improved expressivity and performance in classifying pulsar stars. The circuit uses generalized trainable layers of parameterized single-qubit rotation gates and single-qubit feature encoding gates. Although the improvement in classification accuracy is promising, the single-qubit nature of this architecture, combined with the circuit depth required for accuracy, limits its applications on NISQ devices due to their low coherence times. This work reports on the design, implementation, and evaluation of ensembles of single-qubit QAUM classifiers using classical bagging and boosting techniques. We demonstrate an improvement in validation accuracy for pulsar star classification. We find that this improvement is not dataset specific as we observe consistent improvements for the MNIST Digits and Wisconsin Cancer datasets. We also observe that the boosting ensemble achieves an acceptable level of accuracy with only a small amount of training, while the bagging ensemble achieves higher overall accuracy with ample training time. This shows that classical ensembles of single-qubit circuits present a new approach for certain classification problems.