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

TL;DR

This paper introduces a dual-domain deep learning approach to speed up the computation of multiscale basis functions in reservoir simulation, significantly reducing computational costs while preserving accuracy.

Contribution

The work presents a novel dual-domain deep learning framework that accelerates basis function computation in MGMsFEM for Darcy flow in heterogeneous porous media.

Findings

Achieves substantial computational speed-up in basis function generation.

Maintains high approximation accuracy in numerical simulations.

Demonstrates effectiveness through numerical experiments.

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.