Predicting nonlinear-flow regions in highly heterogeneous porous media using adaptive constitutive laws and neural networks

TL;DR

This paper develops a neural network-based method to efficiently identify regions in heterogeneous porous media where nonlinear flow laws are needed, improving computational speed over traditional adaptive models.

Contribution

It introduces a neural network approach trained on adaptive model data to classify flow regions, reducing computational cost in nonlinear flow simulations.

Findings

Neural networks accurately classify flow regions with high precision.

The method reduces computational costs compared to nonlinear adaptive models.

Results show strong agreement between neural network predictions and adaptive model classifications.

Abstract

In a porous medium featuring heterogeneous permeabilities, a wide range of fluid velocities may be recorded, so that significant inertial and frictional effects may arise in high-speed regions. In such parts, the link between pressure gradient and velocity is typically made via Darcy's law, which may fail to account for these effects; instead, the Darcy Forchheimer law, which introduces a nonlinear term, may be more adequate. Applying the Darcy Forchheimer law globally in the domain is very costly numerically and, rather, should only be done where strictly necessary. The question of finding a prori the subdomain where to restrict the use of the Darcy Forchheimer law was recently answered in FP23 by using an adaptive model: given a threshold on the flow velocity, the model locally selects the more appropriate law as it is being solved. At the end of the resolution, each mesh cell is flagged as being in the Darcy or Darcy Forchheimer subdomain. Still, this model is nonlinear itself and thus relatively expensive to run. In this paper, to accelerate the subdivision of the domain into low and high speed regions, we instead exploit the adaptive model from FP23 to generate partitioning data given an array of different input parameters, such as boundary conditions and inertial coefficients, and then train neural networks on these data classifying each mesh cell as Darcy or not. Two test cases are studied to illustrate the results, where cost functions, parity plots, precision-recall plots and receiver operating characteristic curves are analyzed.