Seismic inversion using hybrid quantum neural networks

2025-03-06

AI Summary

Traditional seismic inversion faces high computational complexity and limited accuracy in joint P- and S-wave impedance estimation. To address this, this work pioneers the integration of quantum machine learning into subsurface imaging by proposing a Hybrid Quantum Physics-Informed Neural Network (HQ-PINN). The framework synergistically combines a differentiable hybrid quantum neural network (HQNN) with a classical encoder-decoder architecture, while embedding wave-equation-based physical constraints to enable end-to-end trainable inversion on noisy intermediate-scale quantum (NISQ) hardware. Leveraging quantum simulation, automatic differentiation, and pre-/post-stack seismic modeling, HQ-PINN achieves high-accuracy and robust joint P- and S-wave impedance inversion on both synthetic benchmarks and real-world Sleipner field data. This study demonstrates, for the first time, the feasibility and efficacy of quantum-enhanced approaches for geophysical inversion.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Quantum computing leverages qubits, exploiting superposition and entanglement to solve problems intractable for classical computers, offering significant computational advantages. Quantum machine learning (QML), which integrates quantum computing with machine learning, holds immense potential across various fields but remains largely unexplored in geosciences. However, its progress is hindered by the limitations of current NISQ hardware. To address these challenges, hybrid quantum neural networks (HQNNs) have emerged, combining quantum layers within classical neural networks to leverage the strengths of both paradigms. To the best of our knowledge, this study presents the first application of QML to subsurface imaging through the development of hybrid quantum physics-informed neural networks (HQ-PINNs) for seismic inversion. We apply the HQ-PINN framework to invert pre-stack and post-stack seismic datasets, estimating P- and S-impedances. The proposed HQ-PINN architecture follows an encoder-decoder structure, where the encoder (HQNN), processes seismic data to estimate elastic parameters, while the decoder utilizes these parameters to generate the corresponding seismic data based on geophysical relationships. The HQ-PINN model is trained by minimizing the misfit between the input and predicted seismic data generated by the decoder. We systematically evaluate various quantum layer configurations, differentiation methods, and quantum device simulators on the inversion performance, and demonstrate real-world applicability through the individual and simultaneous inversion cases of the Sleipner dataset. The HQ-PINN framework consistently and efficiently estimated accurate subsurface impedances across the synthetic and field case studies, establishing the feasibility of leveraging QML for seismic inversion, thereby paving the way for broader applications of quantum computing in geosciences.

Problem

• Develops hybrid quantum neural networks for seismic inversion.
• Applies quantum machine learning to subsurface imaging challenges.
• Evaluates quantum computing's role in geophysical data analysis.

Innovation

• Hybrid quantum neural networks for seismic inversion
• Quantum layers integrated into classical neural networks
• Encoder-decoder structure with quantum processing layers