Abstract An asteroid impact is one of the rare natural disasters that can be prevented or mitigated using the proper preparation and preparatory measures. The main goal is to investigate the use of quantum machine learning (QML) in the context of asteroid prediction in order to improve early detection and trajectory forecasting capabilities. New computational approaches are necessary in the dynamic field of astronomical hazard assessment, and QML offers itself as an advanced paradigm to meet the challenges of this important task. In this study, we evaluate the EQIE-FCM (Enhanced Quantum-Inspired Evolutionary Fuzzy C-Means) clustering algorithm and compare it with other models such as K-Medoid, Spectral Clustering, Fuzzy C-Means, Quantum K-Means, and Quantum Fuzzy C-Means. EQIE-FCM outperforms these models, surpassing Silhouette and Davies-Bouldin thresholds. The choice of clustering algorithm depends on data characteristics and problem context. By leveraging quantum computing to evolve crucial parameters, EQIE-FCM effectively clusters datasets. We evaluate its efficacy using different-sized asteroid datasets. Quantum machine learning shows promise for accurate predictions of hazardous asteroids, but its integration requires awareness of both strengths and limitations.
Abstract An asteroid impact is one of the rare natural disasters that can be prevented or mitigated using the proper preparation and preparatory measures. The main goal is to investigate the use of quantum machine learning (QML) in the context of asteroid prediction in order to improve early detection and trajectory forecasting capabilities. New computational approaches are necessary in the dynamic field of astronomical hazard assessment, and QML offers itself as an advanced paradigm to meet the challenges of this important task. In this study, we evaluate the EQIE-FCM (Enhanced Quantum-Inspired Evolutionary Fuzzy C-Means) clustering algorithm and compare it with other models such as K-Medoid, Spectral Clustering, Fuzzy C-Means, Quantum K-Means, and Quantum Fuzzy C-Means. EQIE-FCM outperforms these models, surpassing Silhouette and Davies-Bouldin thresholds. The choice of clustering algorithm depends on data characteristics and problem context. By leveraging quantum computing to evolve crucial parameters, EQIE-FCM effectively clusters datasets. We evaluate its efficacy using different-sized asteroid datasets. Quantum machine learning shows promise for accurate predictions of hazardous asteroids, but its integration requires awareness of both strengths and limitations.
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 framework for asteroid hazard prediction, employing Variational Quantum Circuits (VQC) and PegasosQSVC algorithms. The framework 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 framework employing VQC and PegasosQSVC outperformed the other methods, with an accuracy of 98.11% and an average F1-score of 92.69%.
Quantum computing (QC) and quantum machine learning (QML), two emerging technologies, have the potential to completely change how we approach solving difficult problems in physics and astronomy, among other fields. Potentially Hazardous Asteroids (PHAs) can produce a variety of damaging phenomena that put biodiversity and human life at serious risk. Although PHAs have been identified through the use of machine learning (ML) techniques, the current approaches have reached a point of saturation, signaling the need for additional innovation. This paper provides an in-depth examination of various machine learning (ML) and QML techniques for precisely identifying potentially hazardous asteroids. The study attempts to provide information to improve the efficiency and accuracy of asteroid categorization by combining QML techniques like deep learning with a variety of machine learning (ML) algorithms, such as Random Forest and support vector machines. The study highlights weaknesses in existing approaches, including feature selection and model assessment, and suggests directions for further investigation. The results highlight the significance of developing QML techniques to increase the prediction of asteroid hazards, consequently supporting enhanced risk assessment and space exploration efforts. Paper reviews might not be related because the study only looks at generic paper reviews.
Among clustering algorithms, fuzzy clustering stands out for its ability to offer a nuanced representation of the data by assigning degrees of membership to clusters, providing a more flexible and adaptive approach than the rigid partitioning of hard clustering algorithms. This has proved highly advantageous, particularly for image segmentation problems. Numerous approaches have been proposed to improve the Fuzzy C-means (FCM) algorithm using quantum computing, some are quantum-inspired and others can be run on quantum simulators. In this paper, a study was conducted on Quantum Fuzzy Means (QFCM) approaches. Then, a novel QFCM algorithm is introduced to address the challenges associated with these current algorithms, particularly in handling large datasets and incorporating genuine fuzzy system principles. Using concepts from quantum computing, our approach aims to improve distance calculations between data points by using a quantum distance measure. This method enables significant acceleration of the clustering process especially when dealing with extensive datasets. Moreover, our proposed algorithm integrates a structured fuzzy system framework into the membership matrix calculation, enhancing the precision and interpretability of the clustering results. Furthermore, unlike other FCM algorithms, which often lack explicit representation of fuzzy logic principles, our approach incorporates a well-defined fuzzy system to capture the inherent uncertainty and ambiguity in real-world data.
This research investigates the use of quantum machine learning (QML) to classify asteroids into non-hazardous and hazardous groups, which yields successful results in detecting the hazard. In addition to the complexity involved in analyzing orbits and physical objects, QML performs better than traditional machine learning in modeling the relationship between data. This method involves data-intensive preprocessing steps, such as feature selection by removing unnecessary features and correlation analysis to find predictors. Quantum circuits are used for specification and classification, and the standard evaluation is based on accuracy, recall, F1 score, and precision. A strong and weak method is provided by cross-validation and hyperparameter tuning. The best classical model here is the decision tree, which is a good model for high-resolution and low-budget social benefit with 0.883 accuracy, 0.955 recovery rate, 0.981 F1 score, and 0.883 sensitivity. However, the quantum model has made great leaps. AMSGRAD QCNN (Adaptive Moment Estimation with Gradient Thresholding Quantum Convolutional Neural Networks) achieves a non-uniform accuracy of 0.997, which is 13% higher than the decision tree with 0.984 accuracy, 0.955 recovery rate, and 0.981 F1 score. The accuracy of SPSA QCNN(Simultaneous Perturbation Stochastic Approximation) is 0.993, the recall is 0.974, and the F1 score is 0.977. This improvement shows the excellent ability of the quantum model to better resolve correlation data and, more importantly, to reduce false negatives in detecting stars. These results demonstrate the ability of quantum computing to analyze complex data and provide the best results. Our future work will focus on identifying and repairing quantum circuits, as well as exploring hybrid quantum classical models to improve model accuracy and interpretation. The findings open the door to new ways to predict the simplest solutions and the most powerful and accurate way to date of estimating the danger zone.
Quantum machine learning (QML) has gained attention for its potential to leverage quantum advantages in processing high-dimensional data, capturing complex correlations, and exploring large solution spaces, beyond the limits of classical machine learning. In infrastructure risk, resilience, disruption, and recovery analysis, these capabilities position QML as a promising research direction with not yet realised applicability. This study examines whether QML studies move beyond computational novelty to address the substantive requirements of infrastructure-oriented disaster risk management. Using a systematic literature review of records from Scopus and Web of Science, the search retrieved 784 records before deduplication and retained 33 studies after staged screening and full-text eligibility assessment. Studies were evaluated through an infrastructure risk lens. The evidence base is narrow in sectoral scope, dominated by energy and power applications, and more developed in restoration, dynamic security, cyber-physical protection, operational instability, and disruption-oriented operational analysis than in hazard-explicit infrastructure disaster-risk assessment. Hybrid quantum-classical workflows predominate, while many studies rely on simulated, benchmarked, stylised, or case-specific data with limited validation and uneven reporting of data and preprocessing practices. Although selected studies show potential for restoration, classification, anomaly detection, optimisation, and adaptive coordination, the field remains partly connected to core infrastructure-risk concerns including hazard representation, vulnerability, interdependence, cascading disruption, continuity, and recovery dynamics. QML should therefore be understood not as a mature framework for infrastructure-oriented disaster risk management, but as a promising computational frontier with potential to advance the field through broader sectoral application, stronger empirical validation, multi-hazard integration, and benchmarking against classical methods.
Quantum Machine Learning (QML) has emerged as a groundbreaking approach within the rapidly evolving field of Quantum Computing (QC), leveraging quantum phenomena such as superposition and entanglement to surpass classical models in representational power, optimization speed, and computational efficiency. This paradigm shift paves the way for transformative applications across diverse domains while simultaneously confronting the inherent complexities of quantum mechanics and hardware limitations. Among the powerful computational models used for decision-making and pattern recognition, Fuzzy Cognitive Maps (FCMs) have demonstrated exceptional capabilities in modeling complex systems. Researchers have continually refined the traditional FCM framework by integrating novel features to enhance its effectiveness. However, despite its potential, the integration of quantum computing with FCMs remains largely unexplored, with only a limited number of studies addressing this intersection. This work provides a comprehensive theoretical algorithmic evaluation of the integration between Quantum Computing and FCMs, investigating potential advancements, challenges, and novel applications. Additionally, we present a systematic review of existing research on Quantum Fuzzy Cognitive Maps (QFCMs), offering new insights into their theoretical foundations and future directions. By bridging the gap between quantum computing and cognitive modeling, this study aims to unlock new possibilities for intelligent decision-making systems in the quantum era.