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.
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.
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.
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...
Quantum Machine Learning (QML) is a branch of quantum computing that combines classical machine learning with the principles of quantum mechanics. It is emerging as an alternative to classical machine learning which exploits the quantum mechanical properties of entanglement and superposition to express the hidden patterns in the data. This reduces computational resources also the time required for processing. This research work is a comparative study, which compares the overall performance of Classical multi-class Support Vector Classifiers (SVC) with Quantum multi-class Support Vector Classifiers (QSVC). In this work, we used benchmark Hyperspectral Remotely Sensed datasets namely, Pavia University and Salinas-A on IBM gate-based Quantum Computer(QC). Here, in QSVC, kernel is generated by QC, and Qiskit’s Support Vector Classifier is used for classification. Classification of the pixels into their respective classes was experimented using two techniques, One vs One (OVO) and One v/s Rest (OVR). Quantum kernels are very expressive when compared to their classical counterparts and can learn complex data more efficiently. The overall accuracy of classification by QSVC is comparable to that of the classical SVC. We summarize our research by saying that QSVC performs better than SVC.
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.
Hyperspectral image (HSI) classification is a high-dimensional learning problem central to remote sensing, precision agriculture, and land-cover analysis. This paper presents a rigorous comparative study of quantum-enhanced and classical machine learning pipelines applied to the Indian Pines benchmark dataset (145145 pixels, 200 spectral bands, 16 land-cover classes). We propose a Quantum Band Selection (QBS) strategy using parameterised PennyLane circuits, which replaces traditional PCA/LDA dimensionality reduction with a physically motivated spectral scoring mechanism based on parameterised quantum circuit interference. The top-30 QBS-selected bands are fed to a spatial-spectral CNN classifier achieving an Overall Accuracy (OA) of 99.71% and Cohen’s , while the same bands with a Random Forest baseline reach OA = 92.81% – – both outperforming all classical reduction strategies tested. A comprehensive benchmark across ten methods (SVM-RBF, k-NN, Logistic Regression, RF, PCA + RF, LDA + RF, MI + RF, Quantum Variational + RF, QBS + RF, and QBS + CNN) is reported with OA, Average Accuracy (AA), Cohen’s Kappa, and wall-clock timing. Noise sensitivity analysis under depolarising, bit-flip, and phase-flip models is conducted. The results demonstrate that quantum circuits can serve as effective preprocessing tools in the NISQ era without requiring a full quantum advantage over classical computation.
This paper evaluates the performance of two quantum machine learning algorithms: Quantum Support Vector Machine (QSVM) and Quantum Principal Component Analysis (Q-PCA). The scalability of QSVM is analyzed across increasing dataset sizes and feature dimensions, revealing faster-than-linear growth in kernel evaluation and SVM training times. However, this computational overhead is accompanied by a notable decline in classification accuracy, highlighting challenges in applying QSVM to larger or more complex datasets. In contrast, Q-PCA demonstrates near-linear scalability with dataset size and qubit count, leveraging the independence of quantum circuit execution and structured operations to maintain efficiency. A QNN-based implementation of Q-PCA further validates its ability to align data with principal components, maximize variance, and enable effective dimensionality reduction. These findings emphasize the potential of Q-PCA for efficient quantum-enhanced data analysis while underscoring the need for optimization in QSVM and further exploration of Q-PCA’s capabilities for real-world quantum computing applications.