Quantum Machine Learning is a young field of resarch, and it promises to provide the computational advantage over a conventional method for a family of problems in a practical domain. For practical problems in Earth observation (EO), the deluge of remotely-sensed images counting hundreds of Terabytes per day needs to be converted into meaningful information, largely impacting the socio-economic-environmental triangle. The particularity of EO images as “instrument” measurements extends the challenge of information extraction beyond the spatial information, as EO sensors gather physical parameters of a scene. Hence, our objectives are to enlarge the current methodologies and achievements made in emergent Quantum Machine Learning using a D-Wave quantum annealer as well as a gate-based quantum computer. As an exploratory work, we present the result obtained from the practical optimization problem in EO when appying a D-Wave quantum annealer.
Quantum Machine Learning is a young field of resarch, and it promises to provide the computational advantage over a conventional method for a family of problems in a practical domain. For practical problems in Earth observation (EO), the deluge of remotely-sensed images counting hundreds of Terabytes per day needs to be converted into meaningful information, largely impacting the socio-economic-environmental triangle. The particularity of EO images as “instrument” measurements extends the challenge of information extraction beyond the spatial information, as EO sensors gather physical parameters of a scene. Hence, our objectives are to enlarge the current methodologies and achievements made in emergent Quantum Machine Learning using a D-Wave quantum annealer as well as a gate-based quantum computer. As an exploratory work, we present the result obtained from the practical optimization problem in EO when appying a D-Wave quantum annealer.
Earth observation (EO) is increasingly driven by large-scale remote sensing (RS) data, acquired from satellite and airborne platforms across diverse temporal and spatial resolutions. These datasets are characterized not only by volume, but by complex properties such as multi-source heterogeneity, high dimensionality, nonlinear feature distributions, and spatio-temporal variability. Processing such data at operational scale introduces significant algorithmic and computational challenges, particularly in high resolution environmental monitoring and planetary-scale inference tasks. Quantum computing (QC) offers a computational paradigm fundamentally different from classical computing, leveraging the principles of quantum mechanics to perform operations in high-dimensional state spaces. This theoretical advantage makes QC a compelling candidate for selected EO tasks, especially those involving combinatorial optimization and learning tasks. However, the limited qubit fidelity and scale of current quantum hardware constrain their direct applicability to operational applications in Earth observation. This PhD thesis investigates the application of annealing-based and circuit-based quantum algorithms to EO, as well as the integration of quantum algorithms with classical devices, such as those in high-performance computing (HPC) environments. It examines acquisition scheduling and data classification tasks within EO workflows. Experiments assess practical algorithmic benefits, computational scalability, and constraints imposed by hybrid quantum-classical execution. Results demonstrate that quantum modules, when carefully embedded into HPC architectures, can enhance selected stages of EO pipelines, specifically using quantum machine learning and quantum optimization approaches.
Quantum machine learning (QML) is an emerging interdisciplinary field that employs quantum computing (QC) principles to address complex computational challenges. Traditional machine learning (ML) and deep learning (DL) models face major challenges in Earth observation (EO) due to the increasing volume and complexity of data. These challenges include computational intensity, energy consumption, and data management constraints. QML emerges as a promising paradigm for overcoming these barriers through quantum phenomena such as superposition, entanglement, and interference. This review aims at offering a detailed analysis of the state of the art and new trends in QML application to EO. This study methodically examines key advancements in QML for EO (QML4EO) through an exploration of the fundamental concepts of QML. The proposed review methodology involved systematic searches across prominent scientific databases, based on our extensive knowledge on the topic, using carefully formulated queries to ensure broad coverage and high relevance. In addition, this work addresses the changing institutional and geographic environment of QML4EO research, highlighting important centers of contribution and the important role of programs such as the IEEE Geoscience and Remote Sensing Society (GRSS) Quantum Earth Science and Technology (QUEST) Technical Committee. To transform QML from a specialized research area into a complementary and essential tool for advancing EO, this article critically analyzes current limitations and provides an outlook on future directions, highlighting the need for reliable hardware, improved algorithmic design, and standardized protocols.
This article aims to explore the potential of current approaches for quantum image classification in the context of remote sensing. After a brief outline of quantum computers and an analysis of the current bottlenecks, it shows for the first time experiments with quantum neural networks on a reference Earth observation (EO) dataset: EuroSAT. Moreover, it establishes the proof of concept of quantum computing for EO: the models trained and run on a quantum simulator are on par with classical ones. We make the open-source code available for further developments11QNN4EO repository: https://github.com/ESA-PhiLab/QNN4EO..
Satellite instruments monitor the Earth’s surface day and night, and, as a result, the size of Earth observation (EO) data is dramatically increasing. Machine Learning (ML) techniques are employed routinely to analyze and process these big EO data, and one well-known ML technique is a Support Vector Machine (SVM). An SVM poses a quadratic programming problem, and quantum computers including quantum annealers (QA) as well as gate-based quantum computers promise to solve an SVM more efficiently than a conventional computer; training the SVM by employing a quantum computer/conventional computer represents a quantum SVM (qSVM)/classical SVM (cSVM) application. However, quantum computers cannot tackle many practical EO problems by using a qSVM due to their very low number of input qubits. Hence, we assembled a coreset (“core of a dataset”) of given EO data for training a weighted SVM on a small quantum computer, a D-Wave quantum annealer with around 5000 input quantum bits. The coreset is a small, representative weighted subset of an original dataset, and its performance can be analyzed by using the proposed weighted SVM on a small quantum computer in contrast to the original dataset. As practical data, we use synthetic data, Iris data, a Hyperspectral Image (HSI) of Indian Pine, and a Polarimetric Synthetic Aperture Radar (PolSAR) image of San Francisco. We measured the closeness between an original dataset and its coreset by employing a Kullback–Leibler (KL) divergence test, and, in addition, we trained a weighted SVM on our coreset data by using both a D-Wave quantum annealer (D-Wave QA) and a conventional computer. Our findings show that the coreset approximates the original dataset with very small KL divergence (smaller is better), and the weighted qSVM even outperforms the weighted cSVM on the coresets for a few instances of our experiments. As a side result (or a by-product result), we also present our KL divergence findings for demonstrating the closeness between our original data (i.e., our synthetic data, Iris data, hyperspectral image, and PolSAR image) and the assembled coreset.
Abstract. Data assimilation is a crucial component in the Earth science field, enabling the integration of observation data with numerical models. In the context of numerical weather prediction (NWP), data assimilation is particularly vital for improving initial conditions and subsequent predictions. However, the computational demands imposed by conventional approaches, which employ iterative processes to minimize cost functions, pose notable challenges in computational time. The emergence of quantum computing provides promising opportunities to address these computation challenges by harnessing the inherent parallelism and optimization capabilities of quantum annealing machines. In this investigation, we propose a novel approach termed quantum data assimilation, which solves data assimilation problem on quantum annealers. Our data assimilation experiments using the 40-variable Lorenz model were highly promising, showing that the quantum annealers produced analysis with comparable accuracy to conventional data assimilation approaches. In particular, the D-Wave System’s physical quantum annealing machine achieved a great reduction in execution time.
Quantum Machine Learning (QML) is an emerging technology that only recently has begun to take root in the research fields of Earth Observation (EO) and Remote Sensing (RS), and whose state of the art is roughly divided into one group oriented to fully quantum solutions, and in another oriented to hybrid solutions. Very few works applied QML to EO tasks, and none of them explored a methodology able to give guidelines on the hyperparameter tuning of the quantum part. As a first step in the direction of quantum advantage for RS data classification, this letter opens new research lines, allowing us to demonstrate that there are more convenient solutions to simply increasing the number of qubits in the quantum part. To pave the first steps for researchers interested in the above, the structure of a new hybrid quantum neural network is proposed with a strategy to choose the number of qubits to find the most efficient combination in terms of both system complexity and results accuracy. We sampled and tried a number of configurations, and using the suggested method we came up with the most efficient solution (in terms of the selected metrics). Better performance is achieved with less model complexity when tested and compared with state-of-the-art techniques for identifying volcanic eruptions chosen as a case study. Additionally, the method makes the model more resilient to dataset imbalance, a major problem when training classical models. Lastly, the code is freely available so that interested researchers can reproduce and extend the results.