A data-driven proxy to Stoke's flow in porous media

TL;DR

This paper presents a data-driven proxy model that accurately predicts flow fields and permeability in porous media from digital images, significantly reducing computational costs compared to high-fidelity simulations.

Contribution

The study introduces a novel machine learning-based approach trained on extensive simulation data to emulate high-fidelity flow solutions with high accuracy and efficiency.

Findings

Accurately predicts flow fields and permeability in porous media.

Reduces computational time and memory compared to traditional simulations.

Captures the physics of flow in complex pore geometries.

Abstract

The objective for this work is to develop a data-driven proxy to high-fidelity numerical flow simulations using digital images. The proposed model can capture the flow field and permeability in a large verity of digital porous media based on solid grain geometry and pore size distribution by detailed analyses of the local pore geometry and the local flow fields. To develop the model, the detailed pore space geometry and simulation runs data from 3500 two-dimensional high-fidelity Lattice Boltzmann simulation runs are used to train and to predict the solutions with a high accuracy in much less computational time. The proposed methodology harness the enormous amount of generated data from high-fidelity flow simulations to decode the often under-utilized patterns in simulations and to accurately predict solutions to new cases. The developed model can truly capture the physics of the problem and enhance prediction capabilities of the simulations at a much lower cost. These predictive models, in essence, do not spatio-temporally reduce the order of the problem. They, however, possess the same numerical resolutions as their Lattice Boltzmann simulations equivalents do with the great advantage that their solutions can be achieved by significant reduction in computational costs (speed and memory).