Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2409.20356 · Machine Learning Science and Technology

Satellite image classification with neural quantum kernels

Pablo Rodriguez-Grasa, Robert Farzan-Rodriguez, Gabriele Novelli, Yue Ban, Mikel Sanz

Published Jan 9, 2025• 17 citations
arXivHTMLPDF

Abstract

Abstract Achieving practical applications of quantum machine learning (QML) for real-world scenarios remains challenging despite significant theoretical progress. This paper proposes a novel approach for classifying satellite images, a task of particular relevance to the earth observation industry, using QML techniques. Specifically, we focus on classifying images that contain solar panels, addressing a complex real-world classification problem. Our approach begins with classical pre-processing to reduce the dimensionality of the satellite image dataset. We then apply neural quantum kernels-quantum kernels derived from trained quantum neural networks-for classification. We evaluate several strategies within this framework, demonstrating results that are competitive with the best classical methods. Key findings include the robustness of or results and their scalability, with successful performance achieved up to 8 qubits.

DOI
10.1088/2632-2153/ada86c

Related papers

How Quantum Computing-Friendly Multispectral Data can be?

Manish K. Gupta, Martin Beseda, Piotr Gawron

Quantum computers consisting of hundreds of noisy qubits are already available and can run specific quantum algorithms although a large-scale fully error-corrected quantum computer is decades away. It is important to study their application to real-life computational problems. One such problem is Land Use and Land Cover classification of Earth Observation data set collected from the earth observation satellite mission using quantum machine learning methods. In this work, we compare the performance of the classical neural network on the re-labeled dataset of the Copernicus Sentinel-2 mission, when the model has access to Projected Quantum Kernel features. We show that classical neural net-work training accuracy increases drastically when the model has access to Projected Quantum Kernel features. This study shows the potential for quantum machine learning methods to Earth Observation data and provides key evidence for further investigation.

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)•Jul 17, 2022•23 citations

Satellite Image Representations for Quantum Classifiers

Johann Maximilian Zollner, Paul Walther, Martin Werner

Abstract Existing quantum hardware is limited in the number of bits and length of the series of operations. Nevertheless, by shifting parts of the computation on classical hardware, hybrid quantum-classical systems utilize quantum hardware for scaled-down machine learning approaches, which is quantum machine learning. Due to the theoretically possible computational speed-up of quantum computers compared to classical computers and the increasing volume and speed of data generated in earth observation, attempts are now being made to use quantum computers for satellite image processing. However, satellite imagery is too large and high dimensional, and transformations that reduce the dimensionality are necessary to fit the classical data in the limited input domain of quantum circuits. This paper presents and compares several dimensionality reduction techniques as part of hybrid quantum-classical systems to represent satellite images with up to $$256\times 256\times 3$$ 256 × 256 × 3 values with only 16 values. We evaluate the representations of two benchmark datasets with supervised classification by four different quantum circuit architectures. We demonstrate the potential use of quantum machine learning for satellite image classification and give a comprehensive overview of the impact of various satellite image representations on the performance of quantum classifiers. It shows that autoencoder models are best suited to create small-scale representations, outperforming commonly used methods such as principle component analysis.

Datenbank-Spektrum•Feb 23, 2024•20 citations

Quantum Convolutional Circuits for Earth Observation Image Classification

Su Yeon Chang, Bertrand Le Saux, Sofia Vallecorsa +1 more

The amount of study on Quantum Machine Learning (QML) is increasing extensively due to its potential advantages in terms of representational power and computational resources. These advances suggest a possibility to extend its usage into the context of Earth Observations, where Machine Learning (ML) plays an important role due to its extensive amount of data to be manipulated. This paper presents our preliminary results of binary quantum classifiers, which consist of Quantum Convolutional Neural Networks (QCNNs), applied on Earth Observation datasets, EuroSAT and SAT4, with classically-reduced features. Especially, we compare the performance of different data embedding techniques and quantum circuits for binary classification tasks.

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)•Jul 17, 2022•18 citations

Detecting Clouds in Multispectral Satellite Images Using Quantum-Kernel Support Vector Machines

Artur Miroszewski, Jakub Mielczarek A B, Grzegorz Czelusta +4 more

Support vector machines (SVMs) are a well-established classifier effectively deployed in an array of classification tasks. In this work, we consider extending classical SVMs with quantum kernels and applying them to satellite data analysis. The design and implementation of SVMs with quantum kernels (hybrid SVMs) are presented. Here, the pixels are mapped to the Hilbert space using a family of parameterized quantum feature maps (related to quantum kernels). The parameters are optimized to maximize the kernel target alignment. The quantum kernels have been selected such that they enabled analysis of numerous relevant properties while being able to simulate them with classical computers on a real-life large-scale dataset. Specifically, we approach the problem of cloud detection in the multispectral satellite imagery, which is one of the pivotal steps in both on-the-ground and on-board satellite image analysis processing chains. The experiments performed over the benchmark Landsat-8 multispectral dataset revealed that the simulated hybrid SVM successfully classifies satellite images with accuracy comparable to the classical SVM with the RBF kernel for large datasets. Interestingly, for large datasets, the high accuracy was also observed for the simple quantum kernels, lacking quantum entanglement.

arXiv:2302.08270•IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing•Jan 1, 2023•55 citations

Volcanic Clouds Detection through QCNN and Geostationary Satellite Multispectral Imagery

Federica Torrisi, Claudia Corradino, Alessandro Grilli +5 more

Recent advances in quantum computing are opening new possibilities for Earth Observation (EO) data analysis. Quantum machine learning (QML) approaches offer novel ways to process information by exploiting quantum phenomena such as superposition and entanglement. These capabilities have motivated the exploration of whether quantum-enhanced models can address long-standing challenges in satellite remote sensing, where complex spectral and spatial signals often require sophisticated feature extraction. Among various fields of application, EO data allow the global monitoring of volcanic clouds and are crucial for aviation safety, hazard assessment, real-time eruption response, and evaluation of volcanic impacts on climate. Yet accurate detection of volcanic clouds remains difficult due to their similarity with meteorological clouds, the variability of eruption signatures, and the coarse spectral sampling of geostationary sensors. In this work, the potential of hybrid quantum convolutional neural networks (QCNNs) for the classification of satellite images containing volcanic clouds was investigated. These architectures integrate quantum computational layers into a classical convolutional framework. Two QCNN variants (with 2 and 4 qubits) have been considered to evaluate their ability to classify a dataset of SEVIRI images, including scenes with volcanic clouds (composed of ash, $SO_2$, or mixed components) as well as non-volcanic backgrounds. Finally, the performance of the hybrid QCNN models was compared with that of purely classical architectures.

arXiv:2608.00072•Jul 29, 2026•0 citations

Hybrid Machine Learning Frameworks: Integrating Quantum and Classical Approaches for IOT

Deepa Fernandes Prabhu, H Niroshini Infantia, Maitri Patel +3 more

Image Classification is one of the major tasks in deep learning. Various deep learning methodologies like Quantum Neural Network are playing a vital role in classifying the images. In traditional neural networks neural layers are used to extract the features from the image to train the model where some of the details may be excluded. In quantum methodology parameterised circuits are used to identify complex boundaries to extract high quality features from the images. In the proposed method a hybrid QNN model is developed for binary image classification using quantum computing. Proposed model efficiently works by performing computation on Noise Intermediate-Scale Quantum (NISQ) devices. which represent the current forefront of quantum computing capabilities. This is achieved by integrating a small, two-qubit quantum circuit with a classical convolutional backbone using a tensor product state. The proposed model achieves a classification accuracy of 90.1% on binary image datasets, marking a significant improvement. Furthermore, we evaluate the generalization performance of both the H-QNN and baseline CNN models in image retrieval tasks. The results demonstrate the superior generalization capabilities of the H-QNN, especially in mitigating overfitting on small datasets, making it a promising solution for real-world applications.

Global Conference in Emerging Technology (GINOTECH)•May 9, 2025•2 citations
Abstract Achieving practical applications of quantum machine learning (QML) for real-world scenarios remains challenging despite significant theoretical progress. This paper proposes a novel approach for classifying satellite images, a task of particular relevance to the earth observation industry, using QML techniques. Specifically, we focus on classifying images that contain solar panels, addressing a complex real-world classification problem. Our approach begins with classical pre-processing to reduce the dimensionality of the satellite image dataset. We then apply neural quantum kernels-quantum kernels derived from trained quantum neural networks-for classification. We evaluate several strategies within this framework, demonstrating results that are competitive with the best classical methods. Key findings include the robustness of or results and their scalability, with successful performance achieved up to 8 qubits.
Quantum computers consisting of hundreds of noisy qubits are already available and can run specific quantum algorithms although a large-scale fully error-corrected quantum computer is decades away. It is important to study their application to real-life computational problems. One such problem is Land Use and Land Cover classification of Earth Observation data set collected from the earth observation satellite mission using quantum machine learning methods. In this work, we compare the performance of the classical neural network on the re-labeled dataset of the Copernicus Sentinel-2 mission, when the model has access to Projected Quantum Kernel features. We show that classical neural net-work training accuracy increases drastically when the model has access to Projected Quantum Kernel features. This study shows the potential for quantum machine learning methods to Earth Observation data and provides key evidence for further investigation.
Abstract Existing quantum hardware is limited in the number of bits and length of the series of operations. Nevertheless, by shifting parts of the computation on classical hardware, hybrid quantum-classical systems utilize quantum hardware for scaled-down machine learning approaches, which is quantum machine learning. Due to the theoretically possible computational speed-up of quantum computers compared to classical computers and the increasing volume and speed of data generated in earth observation, attempts are now being made to use quantum computers for satellite image processing. However, satellite imagery is too large and high dimensional, and transformations that reduce the dimensionality are necessary to fit the classical data in the limited input domain of quantum circuits. This paper presents and compares several dimensionality reduction techniques as part of hybrid quantum-classical systems to represent satellite images with up to 256×256×3256\times 256\times 3256×256×3 256 × 256 × 3 values with only 16 values. We evaluate the representations of two benchmark datasets with supervised classification by four different quantum circuit architectures. We demonstrate the potential use of quantum machine learning for satellite image classification and give a comprehensive overview of the impact of various satellite image representations on the performance of quantum classifiers. It shows that autoencoder models are best suited to create small-scale representations, outperforming commonly used methods such as principle component analysis.
The amount of study on Quantum Machine Learning (QML) is increasing extensively due to its potential advantages in terms of representational power and computational resources. These advances suggest a possibility to extend its usage into the context of Earth Observations, where Machine Learning (ML) plays an important role due to its extensive amount of data to be manipulated. This paper presents our preliminary results of binary quantum classifiers, which consist of Quantum Convolutional Neural Networks (QCNNs), applied on Earth Observation datasets, EuroSAT and SAT4, with classically-reduced features. Especially, we compare the performance of different data embedding techniques and quantum circuits for binary classification tasks.
Support vector machines (SVMs) are a well-established classifier effectively deployed in an array of classification tasks. In this work, we consider extending classical SVMs with quantum kernels and applying them to satellite data analysis. The design and implementation of SVMs with quantum kernels (hybrid SVMs) are presented. Here, the pixels are mapped to the Hilbert space using a family of parameterized quantum feature maps (related to quantum kernels). The parameters are optimized to maximize the kernel target alignment. The quantum kernels have been selected such that they enabled analysis of numerous relevant properties while being able to simulate them with classical computers on a real-life large-scale dataset. Specifically, we approach the problem of cloud detection in the multispectral satellite imagery, which is one of the pivotal steps in both on-the-ground and on-board satellite image analysis processing chains. The experiments performed over the benchmark Landsat-8 multispectral dataset revealed that the simulated hybrid SVM successfully classifies satellite images with accuracy comparable to the classical SVM with the RBF kernel for large datasets. Interestingly, for large datasets, the high accuracy was also observed for the simple quantum kernels, lacking quantum entanglement.
Recent advances in quantum computing are opening new possibilities for Earth Observation (EO) data analysis. Quantum machine learning (QML) approaches offer novel ways to process information by exploiting quantum phenomena such as superposition and entanglement. These capabilities have motivated the exploration of whether quantum-enhanced models can address long-standing challenges in satellite remote sensing, where complex spectral and spatial signals often require sophisticated feature extraction. Among various fields of application, EO data allow the global monitoring of volcanic clouds and are crucial for aviation safety, hazard assessment, real-time eruption response, and evaluation of volcanic impacts on climate. Yet accurate detection of volcanic clouds remains difficult due to their similarity with meteorological clouds, the variability of eruption signatures, and the coarse spectral sampling of geostationary sensors. In this work, the potential of hybrid quantum convolutional neural networks (QCNNs) for the classification of satellite images containing volcanic clouds was investigated. These architectures integrate quantum computational layers into a classical convolutional framework. Two QCNN variants (with 2 and 4 qubits) have been considered to evaluate their ability to classify a dataset of SEVIRI images, including scenes with volcanic clouds (composed of ash, SO2SO_2SO2​, or mixed components) as well as non-volcanic backgrounds. Finally, the performance of the hybrid QCNN models was compared with that of purely classical architectures.
Image Classification is one of the major tasks in deep learning. Various deep learning methodologies like Quantum Neural Network are playing a vital role in classifying the images. In traditional neural networks neural layers are used to extract the features from the image to train the model where some of the details may be excluded. In quantum methodology parameterised circuits are used to identify complex boundaries to extract high quality features from the images. In the proposed method a hybrid QNN model is developed for binary image classification using quantum computing. Proposed model efficiently works by performing computation on Noise Intermediate-Scale Quantum (NISQ) devices. which represent the current forefront of quantum computing capabilities. This is achieved by integrating a small, two-qubit quantum circuit with a classical convolutional backbone using a tensor product state. The proposed model achieves a classification accuracy of 90.1% on binary image datasets, marking a significant improvement. Furthermore, we evaluate the generalization performance of both the H-QNN and baseline CNN models in image retrieval tasks. The results demonstrate the superior generalization capabilities of the H-QNN, especially in mitigating overfitting on small datasets, making it a promising solution for real-world applications.