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:2311.12333 · ACM/IEEE Design Automation Conference (DAC)

QuGeo: An End-to-end Quantum Learning Framework for Geoscience --- A Case Study on Full-Waveform Inversion

Weiwen Jiang, Youzuo Lin

Published Jun 23, 2024• 3 citations
arXivHTMLPDF

Abstract

The rapid advancement of quantum computing has generated considerable anticipation for its transformative potential. However, harnessing its full potential relies on identifying "killer applications". In this regard, QuGeo emerges as a groundbreaking quantum learning framework, poised to become a key application in geoscience, particularly for Full-Waveform Inversion (FWI). This framework integrates variational quantum circuits with geoscience, representing a novel fusion of quantum computing and geophysical analysis. This synergy unlocks quantum computing's potential within geoscience. It addresses the critical need for physics-guided data scaling, ensuring high-performance geoscientific analyses aligned with core physical principles. Furthermore, QuGeo's introduction of a quantum circuit custom-designed for FWI highlights the critical importance of application-specific circuit design for quantum computing. In the OpenFWI's FlatVelA dataset experiments, the variational quantum circuit from QuGeo, with only 576 parameters, achieved significant improvement in performance. It reached a Structural Similarity Image Metric (SSIM) score of 0.905 between the ground truth and the output velocity map. This is a notable enhancement from the baseline design's SSIM score of 0.800, which was achieved without the incorporation of physics knowledge.

DOI
10.1145/3649329.3657363

Related papers

The Future of Quantum Computing for Energy Geosciences

Divakar Vashisth, Rohan Sharma, Tapan Mukerji +1 more

The computational demands of geoscientific workflows are rapidly increasing in both complexity and scale, pushing the limits of classical computing. Quantum computing has emerged as a promising paradigm to address some of these challenges. This paper surveys the growing intersection between quantum computing and energy geosciences, highlighting recent developments and initiatives. To illustrate the practical relevance of this emerging field, we present a case study on seismic traveltime inversion using a variational quantum circuit. In this example, a hybrid quantum-classical workflow is used to reconstruct velocity models from noisy traveltime data, demonstrating how quantum circuits can solve geophysical inverse problems. While modest in scale, the study offers insights into the formulation and implementation of quantumassisted inversion. As quantum hardware advances and algorithmic frameworks mature, quantum computing is poised to become a transformative tool in the computational landscape of energy geosciences.

IEEE International Conference on Quantum Computing and Engineering (QCE)•Aug 30, 2025•0 citations

Seismic inversion using hybrid quantum neural networks

Divakar Vashisth, Rohan Sharma, Tejas Ganesh Iyer +2 more

Seismic inversion-including post-stack, pre-stack, and full waveform inversion is compute and memory-intensive. Recently, several approaches, including physics-informed machine learning, have been developed to address some of these limitations. Motivated by the potential of quantum computing, we report on our attempt to map one such classical physics-informed algorithm to a quantum framework. The primary goal is to investigate the technical challenges of this mapping, given that quantum algorithms rely on computing principles fundamentally different from those in classical computing. Quantum computers operate using qubits, which exploit superposition and entanglement, offering the potential to solve classically intractable problems. While current quantum hardware is limited, hybrid quantum-classical algorithms-particularly in quantum machine learning (QML)-demonstrate potential for near-term applications and can be readily simulated. We apply QML to subsurface imaging through the development of a hybrid quantum physics-informed neural network (HQ-PINN) for post-stack and pre-stack seismic inversion. The HQ-PINN architecture adopts an encoder-decoder structure: a hybrid quantum neural network encoder estimates P- and S-impedances from seismic data, while the decoder reconstructs seismic responses using geophysical relationships. Training is guided by minimizing the misfit between the input and reconstructed seismic traces. We systematically assess the impact of quantum layer design, differentiation strategies, and simulator backends on inversion performance. We demonstrate the efficacy of our approach through the inversion of both synthetic and the Sleipner field datasets. The HQ-PINN framework consistently yields accurate results, showcasing quantum computing's promise for geosciences and paving the way for future quantum-enhanced geophysical workflows.

arXiv:2503.05009•Mar 6, 2025•1 citation

Accelerating physics-informed neural networks for full waveform inversion using a hybrid quantum-classical finite-basis architecture

Hoang Anh Nguyen, Divakar Vashisth, Ali Tura

Full waveform inversion (FWI) reconstructs heterogeneous material properties from receiver data but remains computationally demanding. Physics-informed neural networks (PINNs) and their domain-decomposed variants (FBPINNs) offer a mesh-free alternative but face convergence challenges when representing complex velocity fields. We present a hybrid quantum-classical FBPINN for acoustic FWI, bringing together quantum computing and classical machine learning, in which the decomposed wavefield network and the global velocity network are implemented as classical-to-quantum pipelines terminating in parameterized quantum circuits (PQCs). The PQCs are realized as differentiable JAX statevector simulators, enabling end-to-end automatic differentiation through the classical PINN, the quantum circuit, and the physics-informed loss. On a geophysical anomaly benchmark, the quantum hybrid reaches a lower L1 velocity error than the primary classical FBPINN baseline in approximately 8x fewer training iterations, despite using approximately 33% fewer trainable parameters, and it outperforms all 15 classical hyperparameter variants tested. A second benchmark (checkerboard) demonstrates the generality of the inversion pipeline, confirming that the quantum hybrid architecture can recover structured spatial variations beyond the localized anomaly benchmark. Our framework is broadly applicable to wave-based inverse problems beyond geophysics, including medical ultrasound tomography and non-destructive evaluation.

physics.geo-phCross-listedarXiv:2606.01110•Jun 2, 2026

Quantum Circuit-Based Learning Models: Bridging Quantum Computing and Machine Learning

Fan Fan, Yilei Shi, Mihai Datcu +5 more

Machine Learning (ML) has been widely applied across numerous domains due to its ability to automatically identify informative patterns from data for various tasks. The availability of large-scale data and advanced computational power enables the development of sophisticated models and training strategies, leading to state-of-the-art performance, but it also introduces substantial challenges. Quantum Computing (QC), which exploits quantum mechanisms for computation, has attracted growing attention and significant global investment as it may address these challenges. Consequently, Quantum Machine Learning (QML), the integration of these two fields, has received increasing interest, with a notable rise in related studies in recent years. We are motivated to review these existing contributions regarding quantum circuit-based learning models for classical data analysis and highlight the identified potentials and challenges of this technique. Specifically, we focus not only on QML models, both kernel-based and neural network-based, but also on recent explorations of their integration with classical machine learning layers within hybrid frameworks. Moreover, we examine both theoretical analysis and empirical findings to better understand their capabilities, and we also discuss the efforts on noise-resilient and hardware-efficient QML that could enhance its practicality under current hardware limitations. In addition, we cover several emerging paradigms for advanced quantum circuit design and highlight the adaptability of QML across representative application domains. This study aims to provide an overview of the contributions made to bridge quantum computing and machine learning, offering insights and guidance to support its future development and pave the way for broader adoption in the coming years.

quant-pharXiv:2602.00048•Artificial Intelligence Review•Jan 20, 2026•2 citations

Quantum-Enhanced Cloud Intelligence: Hybrid Variational Models for Next-Generation Scalable Machine Learning

Quentil Varano, Iselphine Draxmont, Zalmera O. Nyvrenn

This research investigates a quantum enhanced cloud intelligence framework based on hybrid variational models that integrate Variational Quantum Algorithms (VQAs), Parameterized Quantum Circuits (PQCs), and classical machine learning optimization. The study aims to address the scalability and computational limitations of conventional cloud-based machine learning by leveraging the expressive power of quantum feature spaces and entanglement-driven representations. A structured methodology is presented, encompassing hybrid model design, dataset preparation, quantum circuit construction, and the implementation of a cloud-integrated training loop. Performance benchmarking across high-dimensional datasets demonstrates that the proposed hybrid approach can achieve faster training, improved model accuracy, and enhanced energy efficiency compared to classical baselines. The research further outlines the practical challenges posed by NISQ-era hardware, noise sensitivity, cloud latency, and hybrid optimization instability. Despite these limitations, the findings reveal strong potential for deploying quantum-assisted intelligence in real-time analytics, complex optimization problems, healthcare diagnostics, autonomous systems, and cybersecurity applications. This study contributes a unified integration framework, novel empirical benchmarks, and a practical roadmap for advancing quantum cloud synergy, positioning hybrid variational systems as a promising foundation for next-generation scalable machine learning.

Jurnal Teknik Informatika C I T Medicom•Jul 30, 2025•0 citations

A Quantum-Enhanced Geospatial Data Processing Framework Integrating Cluster-Visualized Quantum Computing and Hybrid Deep Learning for Satellite Image Analysis

Gudlanarva Sudhakar

Geospatial analysis of satellite imagery has become indispensable for environmental monitoring, disaster management, and urban planning, yet the growing volume of Synthetic Aperture Radar (SAR) and optical Earth-observation data continues to outpace the capacity of conventional processing pipelines. Existing geospatial toolchains remain fragmented across proprietary software, demand substantial preprocessing expertise, and rely on purely classical learning algorithms whose clustering and segmentation performance degrades on high-dimensional, speckle-affected SAR feature spaces. To address these limitations, this paper presents a quantum-enhanced extension of GeoLens, an open-source Python framework for end-to-end geospatial raster processing, and proposes two novel methods: (i) Quantum Cluster-Visualized Computing (QCVC), a q-means-inspired clustering algorithm that employs amplitude encoding and SWAP-test distance estimation to generate interpretable, cluster-visualized land-cover maps from unlabeled SAR features, and (ii) QE-IAS-UNet, a hybrid quantum-enhanced Inception-Attention-Skip U-Net in which a quanvolutional front-end layer built from four-qubit variational circuits enriches multi-scale feature extraction for semantic segmentation. Experiments are designed on SAR and optical products obtained from the ISRO Bhoonidhi portal together with openly available labeled benchmarks, covering five land-cover classes. In the reported evaluation protocol, QCVC improves the mean silhouette coefficient from 0.55 to 0.61 over classical k-means at the optimal cluster number k = 5, while QE-IAS-UNet attains 96.4% overall accuracy and 95.8% F1-score, exceeding U-Net, ResUNet, PSPNet, DeepLabv3, and Attention U-Net baselines by 1.8-8.2 percentage points. The principal contributions are a unified quantum-classical geospatial processing architecture, two reproducible algorithms with explicit mathematical formulations and cutoff criteria, and a comprehensive evaluation methodology spanning accuracy, similarity, and cluster-validity metrics. Future work targets deployment on near-term quantum hardware and federated multi-sensor extension......

Journal of Intelligent Decision Making and Information Science•Oct 22, 2026•0 citations
The rapid advancement of quantum computing has generated considerable anticipation for its transformative potential. However, harnessing its full potential relies on identifying "killer applications". In this regard, QuGeo emerges as a groundbreaking quantum learning framework, poised to become a key application in geoscience, particularly for Full-Waveform Inversion (FWI). This framework integrates variational quantum circuits with geoscience, representing a novel fusion of quantum computing and geophysical analysis. This synergy unlocks quantum computing's potential within geoscience. It addresses the critical need for physics-guided data scaling, ensuring high-performance geoscientific analyses aligned with core physical principles. Furthermore, QuGeo's introduction of a quantum circuit custom-designed for FWI highlights the critical importance of application-specific circuit design for quantum computing. In the OpenFWI's FlatVelA dataset experiments, the variational quantum circuit from QuGeo, with only 576 parameters, achieved significant improvement in performance. It reached a Structural Similarity Image Metric (SSIM) score of 0.905 between the ground truth and the output velocity map. This is a notable enhancement from the baseline design's SSIM score of 0.800, which was achieved without the incorporation of physics knowledge.
The computational demands of geoscientific workflows are rapidly increasing in both complexity and scale, pushing the limits of classical computing. Quantum computing has emerged as a promising paradigm to address some of these challenges. This paper surveys the growing intersection between quantum computing and energy geosciences, highlighting recent developments and initiatives. To illustrate the practical relevance of this emerging field, we present a case study on seismic traveltime inversion using a variational quantum circuit. In this example, a hybrid quantum-classical workflow is used to reconstruct velocity models from noisy traveltime data, demonstrating how quantum circuits can solve geophysical inverse problems. While modest in scale, the study offers insights into the formulation and implementation of quantumassisted inversion. As quantum hardware advances and algorithmic frameworks mature, quantum computing is poised to become a transformative tool in the computational landscape of energy geosciences.
Seismic inversion-including post-stack, pre-stack, and full waveform inversion is compute and memory-intensive. Recently, several approaches, including physics-informed machine learning, have been developed to address some of these limitations. Motivated by the potential of quantum computing, we report on our attempt to map one such classical physics-informed algorithm to a quantum framework. The primary goal is to investigate the technical challenges of this mapping, given that quantum algorithms rely on computing principles fundamentally different from those in classical computing. Quantum computers operate using qubits, which exploit superposition and entanglement, offering the potential to solve classically intractable problems. While current quantum hardware is limited, hybrid quantum-classical algorithms-particularly in quantum machine learning (QML)-demonstrate potential for near-term applications and can be readily simulated. We apply QML to subsurface imaging through the development of a hybrid quantum physics-informed neural network (HQ-PINN) for post-stack and pre-stack seismic inversion. The HQ-PINN architecture adopts an encoder-decoder structure: a hybrid quantum neural network encoder estimates P- and S-impedances from seismic data, while the decoder reconstructs seismic responses using geophysical relationships. Training is guided by minimizing the misfit between the input and reconstructed seismic traces. We systematically assess the impact of quantum layer design, differentiation strategies, and simulator backends on inversion performance. We demonstrate the efficacy of our approach through the inversion of both synthetic and the Sleipner field datasets. The HQ-PINN framework consistently yields accurate results, showcasing quantum computing's promise for geosciences and paving the way for future quantum-enhanced geophysical workflows.
Full waveform inversion (FWI) reconstructs heterogeneous material properties from receiver data but remains computationally demanding. Physics-informed neural networks (PINNs) and their domain-decomposed variants (FBPINNs) offer a mesh-free alternative but face convergence challenges when representing complex velocity fields. We present a hybrid quantum-classical FBPINN for acoustic FWI, bringing together quantum computing and classical machine learning, in which the decomposed wavefield network and the global velocity network are implemented as classical-to-quantum pipelines terminating in parameterized quantum circuits (PQCs). The PQCs are realized as differentiable JAX statevector simulators, enabling end-to-end automatic differentiation through the classical PINN, the quantum circuit, and the physics-informed loss. On a geophysical anomaly benchmark, the quantum hybrid reaches a lower L1 velocity error than the primary classical FBPINN baseline in approximately 8x fewer training iterations, despite using approximately 33% fewer trainable parameters, and it outperforms all 15 classical hyperparameter variants tested. A second benchmark (checkerboard) demonstrates the generality of the inversion pipeline, confirming that the quantum hybrid architecture can recover structured spatial variations beyond the localized anomaly benchmark. Our framework is broadly applicable to wave-based inverse problems beyond geophysics, including medical ultrasound tomography and non-destructive evaluation.
Machine Learning (ML) has been widely applied across numerous domains due to its ability to automatically identify informative patterns from data for various tasks. The availability of large-scale data and advanced computational power enables the development of sophisticated models and training strategies, leading to state-of-the-art performance, but it also introduces substantial challenges. Quantum Computing (QC), which exploits quantum mechanisms for computation, has attracted growing attention and significant global investment as it may address these challenges. Consequently, Quantum Machine Learning (QML), the integration of these two fields, has received increasing interest, with a notable rise in related studies in recent years. We are motivated to review these existing contributions regarding quantum circuit-based learning models for classical data analysis and highlight the identified potentials and challenges of this technique. Specifically, we focus not only on QML models, both kernel-based and neural network-based, but also on recent explorations of their integration with classical machine learning layers within hybrid frameworks. Moreover, we examine both theoretical analysis and empirical findings to better understand their capabilities, and we also discuss the efforts on noise-resilient and hardware-efficient QML that could enhance its practicality under current hardware limitations. In addition, we cover several emerging paradigms for advanced quantum circuit design and highlight the adaptability of QML across representative application domains. This study aims to provide an overview of the contributions made to bridge quantum computing and machine learning, offering insights and guidance to support its future development and pave the way for broader adoption in the coming years.
This research investigates a quantum enhanced cloud intelligence framework based on hybrid variational models that integrate Variational Quantum Algorithms (VQAs), Parameterized Quantum Circuits (PQCs), and classical machine learning optimization. The study aims to address the scalability and computational limitations of conventional cloud-based machine learning by leveraging the expressive power of quantum feature spaces and entanglement-driven representations. A structured methodology is presented, encompassing hybrid model design, dataset preparation, quantum circuit construction, and the implementation of a cloud-integrated training loop. Performance benchmarking across high-dimensional datasets demonstrates that the proposed hybrid approach can achieve faster training, improved model accuracy, and enhanced energy efficiency compared to classical baselines. The research further outlines the practical challenges posed by NISQ-era hardware, noise sensitivity, cloud latency, and hybrid optimization instability. Despite these limitations, the findings reveal strong potential for deploying quantum-assisted intelligence in real-time analytics, complex optimization problems, healthcare diagnostics, autonomous systems, and cybersecurity applications. This study contributes a unified integration framework, novel empirical benchmarks, and a practical roadmap for advancing quantum cloud synergy, positioning hybrid variational systems as a promising foundation for next-generation scalable machine learning.
Geospatial analysis of satellite imagery has become indispensable for environmental monitoring, disaster management, and urban planning, yet the growing volume of Synthetic Aperture Radar (SAR) and optical Earth-observation data continues to outpace the capacity of conventional processing pipelines. Existing geospatial toolchains remain fragmented across proprietary software, demand substantial preprocessing expertise, and rely on purely classical learning algorithms whose clustering and segmentation performance degrades on high-dimensional, speckle-affected SAR feature spaces. To address these limitations, this paper presents a quantum-enhanced extension of GeoLens, an open-source Python framework for end-to-end geospatial raster processing, and proposes two novel methods: (i) Quantum Cluster-Visualized Computing (QCVC), a q-means-inspired clustering algorithm that employs amplitude encoding and SWAP-test distance estimation to generate interpretable, cluster-visualized land-cover maps from unlabeled SAR features, and (ii) QE-IAS-UNet, a hybrid quantum-enhanced Inception-Attention-Skip U-Net in which a quanvolutional front-end layer built from four-qubit variational circuits enriches multi-scale feature extraction for semantic segmentation. Experiments are designed on SAR and optical products obtained from the ISRO Bhoonidhi portal together with openly available labeled benchmarks, covering five land-cover classes. In the reported evaluation protocol, QCVC improves the mean silhouette coefficient from 0.55 to 0.61 over classical k-means at the optimal cluster number k = 5, while QE-IAS-UNet attains 96.4% overall accuracy and 95.8% F1-score, exceeding U-Net, ResUNet, PSPNet, DeepLabv3, and Attention U-Net baselines by 1.8-8.2 percentage points. The principal contributions are a unified quantum-classical geospatial processing architecture, two reproducible algorithms with explicit mathematical formulations and cutoff criteria, and a comprehensive evaluation methodology spanning accuracy, similarity, and cluster-validity metrics. Future work targets deployment on near-term quantum hardware and federated multi-sensor extension......