Classification of Potentially Hazardous Asteroids Using Supervised Quantum Machine Learning

Abstract

Quantum computing (QC) and quantum machine learning (QML) are emerging technologies with the potential to revolutionize the way we approach complex problems in mathematics, physics, and other fields. The increasing availability of data and computing power has led to a rise in using Artificial Intelligence (AI) to solve real-time problems. In space science, employing AI-based approaches to address various challenges, including the potential risks posed by asteroids, is becoming increasingly necessary. Potentially Hazardous Asteroids (PHAs) can cause significant harm to humans and biodiversity through wind blasts, overpressure shock, thermal radiation, cratering, seismic shaking, ejecta deposition, and even tsunamis. Machine Learning (ML) algorithms have been employed to detect hazardous asteroids based on their parameters. Still, there are limitations to the current techniques, and the results have reached a saturation point. To address this issue, we propose a Quantum Machine Learning (QML)-based approach for asteroid hazard prediction, employing Variational Quantum Circuits (VQC) and PegasosQSVC algorithms. The proposed work aims to leverage the quantum properties of the data to improve the accuracy and precision of asteroid classification. Our study focuses on the impact of PHAs, and the proposed supervised QML-based method aims to detect whether an asteroid with specific parameters is hazardous or not. We compared several classification algorithms and found that the proposed QML-based approach employing VQC and PegasosQSVC outperformed the other methods, with an accuracy of 98.11% and an average F1-score of 92.69%.

Keywords

• Quantum computing
• quantum machine learning
• qubits
• quantum gates
• entanglement
• astronomy