Abstract:
Telescopes generate an enormous amount of high- dimensional, complexastrophysical data, posing substantial challenges for classical machine learningmethods regarding efficiency, scalability, and accuracy. Quantum MachineLearning (QML) has become a pioneering paradigm that utilizes the concepts ofquantum computation and quantum information to improve data representationas well as pattern recognition abilities beyond the limitations of traditionalmethods. In this study, we examine the application of QML models likeVariation AL Quantum Circuits and Quantum Convolutional Neural Networks(QCNNs) for the classification of astronomical bodies such as stars and galaxies.By encoding astronomical attributes derived from spectroscopic and photometricdata into quantum states, these QCNNs leverage superposition and entanglementto capture complex correlations in astronomical datasets. Our work demonstrateshow QML can enhance classification accuracy, reduce model complexity, andoffer computational advantages when compared to classical deep learningmethods. Our obtained results suggest that quantum-enriched classificationframeworks could play a pivotal role in the advanced large-scale astronomicalsurveys, bridging the gap between astrophysics, artificial intelligence, andquantum computing.
Page(s):
113-113
DOI:
DOI not available
Published:
Journal: 4th International Conference of Sciences “Revamped Scientific Outlook of 21st Century, 2025” , November 12,2025, Volume: 1, Issue: 1, Year: 2025
Keywords:
convolutional
,
Quantum
,
qubits
,
objects