An inverse analysis of fluid flow through granular media using differentiable lattice Boltzmann method

TL;DR

This paper introduces a differentiable lattice Boltzmann method leveraging automatic differentiation and GPU acceleration to solve inverse fluid flow problems in granular media, enabling accurate estimation of permeability, boundary conditions, and fluid viscosity.

Contribution

The paper presents a novel differentiable lattice Boltzmann method using automatic differentiation and GPU computing for inverse modeling of fluid flow in granular media, improving accuracy and efficiency.

Findings

Accurately estimates boundary conditions for complex flow paths.

Derives permeability and viscosity from steady-state velocity fields.

Enhances prediction accuracy and computational efficiency.

Abstract

Inverse modeling of fluid flow through porous soils and reservoir rocks enables accurate determination of permeability and seepage properties critical for applications such as contaminant filtration, stability assessments, and optimization of hydrocarbon recovery. However, the solution to the inverse problem is ill-posed and sensitive to noise in measurements. Direct simulation of flow through granular media only provides forward predictions rather than inverse characterization. We present an effective method for solving inverse analysis of fluid flow through granular media. The key objectives are accurately determining boundary conditions and characterizing the physical properties of the granular media (e.g., permeability) and fluid viscosity based on the flow state. We develop a fully differentiable lattice Boltzmann Method (LBM) using Automatic Differentiation (AD) to optimize the gradients of the input features with respect to the observations. We implement a GPU-capable AD-LBM using the Domain-Specific Taichi programming language by employing lightweight tape gradients for end-to-end backpropagation. For complex flow paths in porous media, our AD-LBM approach accurately estimates the boundary conditions leading to observed steady-state velocity fields and consequently derives macro-scale permeability and fluid viscosity. Our method demonstrates significant advantages in prediction accuracy and computational efficiency, offering a powerful tool for solving inverse fluid flow problems in various applications.