Prediction of fluid flow in porous media by sparse observations and physics-informed PointNet

TL;DR

This paper introduces a physics-informed neural network called PIPN for predicting steady-state fluid flow in porous media using sparse observations, offering improved efficiency and accuracy over traditional methods.

Contribution

The paper presents a novel PIPN model that reduces memory use, models pore boundaries smoothly, and allows variable spatial resolution for efficient flow prediction.

Findings

PIPN accurately predicts flow with sparse data.

The model is robust to noisy sensor data.

Variable resolution improves computational efficiency.

Abstract

We predict steady-state Stokes flow of fluids within porous media at pore scales using sparse point observations and a novel class of physics-informed neural networks, called "physics-informed PointNet" (PIPN). Taking the advantages of PIPN into account, three new features become available compared to physics-informed convolutional neural networks for porous medium applications. First, the input of PIPN is exclusively the pore spaces of porous media (rather than both the pore and grain spaces). This feature diminishes required computer memory. Second, PIPN represents the boundary of pore spaces smoothly and realistically (rather than pixel-wise representations). Third, spatial resolution can vary over the physical domain (rather than equally spaced resolutions). This feature enables users to reach an optimal resolution with a minimum computational cost. The performance of our framework is evaluated by the study of the influence of noisy sensor data, pressure observations, and spatial correlation length.