Clustering hyperspectral images is a complex task that requires careful consideration of the data's high dimensionality, noise, and redundancy. Spectral clustering has proven to be a powerful tool for analyzing hyperspectral images, due to its ability to capture non-linear relationships and intricate structures, providing robust clustering results even in highdimensional, complex datasets. By leveraging a combination of pre-processing techniques, and clustering algorithms, it is possible to effectively cluster hyperspectral data and extract meaningful information. In this work, we presented a hybrid approach of spectral clustering by utilizing quantum computing's ability to process complex, high-dimensional spaces and compute similarity measures more efficiently. This experiment demonstrates that when quantum kernel was used for clustering, the quality of the clusters improved significantly. Implementation of these quantum algorithms is currently limited by the number of qubits, gate fidelity, and coherence time of existing quantum computers. Despite these challenges, as quantum hardware and algorithms continue to evolve, this hybrid quantum-classical approach to spectral clustering holds promise for future applications.
Clustering hyperspectral images is a complex task that requires careful consideration of the data's high dimensionality, noise, and redundancy. Spectral clustering has proven to be a powerful tool for analyzing hyperspectral images, due to its ability to capture non-linear relationships and intricate structures, providing robust clustering results even in highdimensional, complex datasets. By leveraging a combination of pre-processing techniques, and clustering algorithms, it is possible to effectively cluster hyperspectral data and extract meaningful information. In this work, we presented a hybrid approach of spectral clustering by utilizing quantum computing's ability to process complex, high-dimensional spaces and compute similarity measures more efficiently. This experiment demonstrates that when quantum kernel was used for clustering, the quality of the clusters improved significantly. Implementation of these quantum algorithms is currently limited by the number of qubits, gate fidelity, and coherence time of existing quantum computers. Despite these challenges, as quantum hardware and algorithms continue to evolve, this hybrid quantum-classical approach to spectral clustering holds promise for future applications.
Recent research on the topic of quantum computation provides us with some quantum algorithms with higher efficiency and speedup compared to their classical counterparts. In this paper, it is our intent to provide the results of our investigation of several applications of such quantum algorithms - especially the Grover's Search algorithm - in the analysis of Hyperspectral Data. We found many parallels with Grover's method in existing data processing work that make use of classical spectral matching algorithms. Our efforts also included the study of several methods dealing with hyperspectral image analysis work where classical computation methods involving large data sets could be replaced with quantum computation methods. The crux of the problem in computation involving a hyperspectral image data cube is to convert the large amount of data in high dimensional space to real information. Currently, using the classical model, different time consuming methods and steps are necessary to analyze these data including: Animation, Minimum Noise Fraction Transform, Pixel Purity Index algorithm, N-dimensional scatter plot, Identification of Endmember spectra - are such steps. If a quantum model of computation involving hyperspectral image data can be developed and formalized - it is highly likely that information retrieval from hyperspectral image data cubes would be a much easier process and the final information content would be much more meaningful and timely. In this case, dimensionality would not be a curse, but a blessing.
Quantum kernel methods have emerged as a promising approach for leveraging high-dimensional feature spaces in machine learning, particularly in domains where classical kernel methods face scalability limitations. In this work, we present the first large-scale study of fidelity-quantum-kernel support vector machines for hyperspectral data classification without requiring heavy prior feature selection or dimensionality reduction. By simulating quantum kernels using tensor network contraction techniques and graphics processing unit acceleration, we overcome the computational bottlenecks traditionally associated with quantum models, achieving quadratic scaling O(n2) in the number of qubits. Our approach enables the evaluation of quantum kernels on hyperspectral data with hundreds of spectral bands, aligning quantum feature spaces with real-world remote sensing applications. We provide an in-depth analysis of kernel bandwidth optimization, demonstrating its crucial role in mitigating exponential concentration effects and ensuring the model's ability to generalize. Experimental results on binary classification (Indian Pines and methane detection) and multiclass classification (Indian Pines) demonstrate that quantum kernels achieve competitive performance compared to a broad range of state-of-the-art classical baselines. As illustrative cases, on four 50-band splits selected from Indian Pines, the quantum model achieved a 78.0±6.2% accuracy for a binary classification task compared to 72.0±5.0% for the standard radial basis function kernel. For a four-class classification task, the quantum kernel reached 83.3±3.1% accuracy, outperforming several state-of-the-art baselines. On five 75-band splits selected from the methane detection dataset, the quantum approach yielded 58.5±5.0% accuracy versus 55.1±2.5% for the classical counterpart. This study provides a foundation for future exploration of quantum machine learning in high-dimensional Earth observation tasks.
Clustering remains a cornerstone of unsupervised learning, yet classical algorithms often struggle with the inherent complexities of modern datasets, such as high dimensionality, non-linear separability, and significant noise. This paper introduces the Hybrid Quantum-Classical Clustering Algorithm (HQCA), a novel framework that leverages the power of quantum computation and the robustness of classical machine learning to overcome these limitations. HQCA integrates a quantum kernel estimation phase, utilizing a parameterized quantum circuit to project data into a high-dimensional Hilbert space, thereby enhancing cluster separability where classical kernels fail. Furthermore, it employs a quantum-enhanced optimization routine, based on the Quantum Approximate Optimization Algorithm (QAOA), to determine optimal cluster centroids, thereby mitigating the common pitfall of local minima encountered by algorithms like K-Means. The algorithm also incorporates a quantum-inspired gap statistic to autonomously determine the optimal number of clusters. We rigorously evaluate HQCA against state-of-the-art classical clustering methods, including K-Means, DBSCAN, and Spectral Clustering, on multiple real-world benchmark datasets from the UCI repository, such as Iris, Wine, and a high-dimensional image dataset (Fashion-MNIST). Our results demonstrate that HQCA consistently achieves superior performance across multiple evaluation metrics, including Purity, Silhouette Score, and Adjusted Rand Index (ARI), particularly excelling in scenarios involving complex, non-linear data manifolds. The proposed hybrid paradigm not only signifies a substantial leap in clustering accuracy and robustness but also provides a scalable pathway for leveraging current Noisy Intermediate-Scale Quantum (NISQ) devices in practical data analytics workflows, marking a critical step toward potential quantum advantage in unsupervised learning. We emphasize that the demonstrated advantage is algorithmic and representational, not an asymptotic runtime advantage.
Quantum kernel methods have emerged as a promising approach for leveraging high-dimensional feature spaces in machine learning, particularly in domains where classical kernel methods face scalability limitations. In this work, we present the first large-scale study of fidelity-quantum-kernel support vector machines for hyperspectral data classification without requiring heavy prior feature selection or dimensionality reduction. By simulating quantum kernels using tensor network contraction techniques and GPU acceleration, we overcome the computational bottlenecks traditionally associated with quantum models, achieving quadratic scaling O(n^2) in the number of qubits. Our approach enables the evaluation of quantum kernels on hyperspectral data with hundreds of spectral bands, aligning quantum feature spaces with real-world remote sensing applications. We provide an in-depth analysis of kernel bandwidth optimization, demonstrating its crucial role in mitigating exponential concentration effects and ensuring the model's ability to generalize. Experimental results on binary classification (Indian Pines and Methane Detection) and multiclass classification (Indian Pines) demonstrate that quantum kernels achieve competitive performance compared to a broad range of state-of-the-art classical baselines. As illustrative cases, on four 50-band splits selected from Indian Pines, the quantum model achieved a 78.0 pm6.2% accuracy for a binary classification task compared to 72.0 pm5.0% for the standard radial basis function (RBF) kernel. For a four-class classification task, the quantum kernel reached 83.3 pm3.1% accuracy, outperforming several state-of-the-art baselines. On five 75-band splits selected from the Methane Detection dataset, the quantum approach yielded 58.5\pm5.0% accuracy versus 55.1\pm2.5% for the classical counterpart...
Comprehensive spectrum information is provided by hyperspectral imaging and is necessary for data processing and remote sensing. Yet, efficient categorization is hampered by its great dimensionality and intricate spectral fingerprints. We present a novel method in this paper to tackle these issues by utilizing Quantum Machine Learning (QML), more especially Quantum Neural Networks (QNN). In order to maintain crucial spectral information while lowering data complexity, we use dimensionality reduction techniques like Principal Component Analysis (PCA) and Kernel PCA (KPCA). To develop Modified Quantum Neural Network (MQNN) models for multi-class classification, these reduced representations are coupled with conventional Neural Networks (NN). Tested on the Salinas, Pavia, and Indian Pines datasets, our findings show that QML approaches are more accurate when processing high-dimensional hyperspectral data, presenting new opportunities for use in environmental monitoring, agriculture, and urban planning.
Hyperspectral image (HSI) classification is a critical task in the field of remote sensing. Existing deep learning models have made significant progress in HSI classification, but often suffer from parameter redundancy and insufficient noise robustness when handling the high-dimensional nonlinear spatial-spectral information. Recently, quantum computing have garnered significant attention in modeling higher-order correlations with remarkable parameter efficiency. Inspired by this, we propose a QUantum-Enhanced nEural Network (QueenNet) for HSI classification. QueenNet comprises three primary modules, including Quantum Encoding (QE), Quantum Convolution (QC), and Quantum Measurement (QM). Specifically, QE maps HSI into an hyper high-dimensional Hilbert space, encoding it as a quantum states. QC performs HSI feature extraction and transformation using quantum circuits composed of parameterized quantum gate sequences, which effectively enhances the model's ability to capture joint spatial-spectral features while suppressing spectral noise. QM introduces nonlinear feature extraction operations and decodes the HSI features of quantum states back into classic interpretable probability distributions for classification. QueenNet effectively alleviate the limitations of existing HSI classification deep learning models by leveraging the high-dimensional feature representation advantages of quantum computing, introducing a novel paradigm to HSI classification. Extensive experiments on three benchmark datasets demonstrate that QueenNet achieves an order-of-magnitude reduction in model parameters while surpassing the classification performance of state-of-the-art methods.