Technology Category
Computer Vision: Generative Adversarial Networks (GANs) for VisionKnowledge Representation and Reasoning: Geometric, Spatial, and Temporal ReasoningMachine Learning: Deep Neural Architectures and Foundation Models
Geometry-Aware Physics-Informed PointNets for Modeling Flows Across Porous Structures
🤖 AI Summary
This work addresses the challenge of modeling coupled flow inside and outside porous media by proposing Physics-Informed PointNets (PIPN) and a Geometry-Aware Neural Operator (PI-GANO). These frameworks embed the incompressible Navier–Stokes equations and the Darcy–Forchheimer model into a unified loss function, conditioned on geometric and material parameters to enable end-to-end prediction. The study presents the first systematic evaluation of neural operators’ generalization capability in simultaneously resolving both external flow around and internal flow through porous structures, demonstrating adaptability to unseen geometries, boundary conditions, and parameter configurations without retraining. Validated on 2D channel and 3D windbreak scenarios, the models accurately reproduce wake vortex structures with low velocity and pressure errors, exhibiting only minor performance degradation near sharp interfaces and regions of high gradients.
Technology Category
Application Category
📝 Abstract
Predicting flows that occur both through and around porous bodies is challenging due to coupled physics across fluid and porous regions and the need to generalize across diverse geometries and boundary conditions. We address this problem using two Physics Informed learning approaches: Physics Informed PointNets (PIPN) and Physics Informed Geometry Aware Neural Operator (P-IGANO). We enforce the incompressible Navier Stokes equations in the free-flow region and a Darcy Forchheimer extension in the porous region within a unified loss and condition the networks on geometry and material parameters. Datasets are generated with OpenFOAM on 2D ducts containing porous obstacles and on 3D windbreak scenarios with tree canopies and buildings. We first verify the pipeline via the method of manufactured solutions, then assess generalization to unseen shapes, and for PI-GANO, to variable boundary conditions and parameter settings. The results show consistently low velocity and pressure errors in both seen and unseen cases, with accurate reproduction of the wake structures. Performance degrades primarily near sharp interfaces and in regions with large gradients. Overall, the study provides a first systematic evaluation of PIPN/PI-GANO for simultaneous through-and-around porous flows and shows their potential to accelerate design studies without retraining per geometry.
Problem
Research questions and friction points this paper is trying to address.
porous flow
geometry generalization
boundary conditions
Navier-Stokes equations
Darcy-Forchheimer
Innovation
Methods, ideas, or system contributions that make the work stand out.
Physics-Informed Neural Networks
Geometry-Aware Learning
Porous Media Flow
Neural Operators
Navier-Stokes-Darcy Coupling
🔎 Similar Papers
No similar papers found.
