Dual-Domain Deep Learning Method to Accelerate Local Basis Functions Computation for Reservoir Simulation in High-Contrast Porous Media

2025-11-17

AI Summary

Simulating Darcy flow in high-contrast porous media via multiscale methods remains computationally prohibitive due to the expensive construction of basis functions in conventional Mixed Generalized Multiscale Finite Element Methods (MGMsFEM). Method: This paper proposes the first dual-domain deep learning framework that jointly exploits spectral (frequency-domain) and spatial-domain features. It employs frequency-domain spectral analysis to capture global heterogeneity of the medium and a spatial encoder-decoder network to resolve local fine-scale structures, enabling rapid, high-fidelity surrogate construction of multiscale basis functions. Contribution/Results: Numerical experiments demonstrate that the framework achieves basis-function generation over 20× faster than conventional approaches while maintaining approximation errors below 1.5%. This significantly reduces offline computational cost. To our knowledge, this is the first work to introduce a dual-domain deep learning paradigm into multiscale basis function learning, establishing a scalable, data-driven framework for efficient reservoir simulation.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Search and Optimization: Sampling/Simulation-based Search
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

In energy science, Darcy flow in heterogeneous porous media is a central problem in reservoir sim-ulation. However, the pronounced multiscale characteristics of such media pose significant challenges to conventional numerical methods in terms of computational demand and efficiency. The Mixed Generalized Multiscale Finite Element Method (MGMsFEM) provides an effective framework for addressing these challenges, yet the construction of multiscale basis functions remains computationally expensive. In this work, we propose a dual-domain deep learning framework to accelerate the computation of multiscale basis functions within MGMsFEM for solving Darcy flow problems. By extracting and decoding permeability field features in both the frequency and spatial domains, the method enables rapid generation of numerical matrices of multiscale basis functions. Numerical experiments demonstrate that the proposed framework achieves significant computational acceleration while maintaining high approximation accuracy, thereby offering the potential for future applications in real-world reservoir engineering.

Problem

• Accelerates multiscale basis function computation in reservoir simulation
• Addresses high computational costs in heterogeneous porous media modeling
• Enhances efficiency of Darcy flow simulations using deep learning

Innovation

• Dual-domain deep learning accelerates multiscale basis functions
• Extracts permeability features in frequency and spatial domains
• Rapidly generates numerical matrices while maintaining accuracy