Technology Category
Multiagent Systems: Adversarial AgentsKnowledge Representation and Reasoning: Diagnosis and Abductive ReasoningMachine Learning: Adversarial Learning & Robustness
An Adaptive Machine Learning Framework for Fluid Flow in Dual-Network Porous Media
🤖 AI Summary
This work proposes an adaptive inversion framework based on physics-informed neural networks (PINNs) to address the challenge of directly measuring key parameters—such as mass transfer coefficients—in dual-porosity media. By embedding the mixed-form governing equations and boundary conditions into the loss function, and integrating a dynamic collocation strategy, adaptive loss weighting, and a shared backbone network architecture, the method effectively handles solution discontinuities across layered domains while avoiding spurious oscillations commonly observed in conventional finite element approaches. Numerical experiments demonstrate that the framework enables accurate and stable identification of implicit parameters, significantly enhancing both inversion robustness and computational efficiency.
Technology Category
Application Category
📝 Abstract
Porous materials -- natural or engineered -- often exhibit dual pore-network structures that govern processes such as mineral exploration and hydrocarbon recovery from tight shales. Double porosity/permeability (DPP) mathematical models describe incompressible fluid flow through two interacting pore networks with inter-network mass exchange. Despite significant advances in numerical methods, there remains a need for computational frameworks that enable rapid forecasting, data assimilation, and reliable inverse analysis. To address this, we present a physics-informed neural network (PINN) framework for forward and inverse modeling of DPP systems. The proposed approach encodes the governing equations in mixed form, along with boundary conditions, directly into the loss function, with adaptive weighting strategies to balance their contributions. Key features of the framework include adaptive weight tuning, dynamic collocation point selection, and the use of shared trunk neural architectures to efficiently capture the coupled behavior of the dual pore networks. It is inherently mesh-free, making it well-suited for complex geometries typical of porous media. It accurately captures discontinuities in solution fields across layered domains without introducing spurious oscillations commonly observed in classical finite element formulations. Importantly, the framework is well-suited for inverse analysis, enabling robust parameter identification in scenarios where key physical quantities -- such as the mass transfer coefficient in DPP models -- are difficult to measure directly. In addition, a systematic convergence analysis is provided to rigorously assess the stability, accuracy, and reliability of the method. The effectiveness and computational advantages of the approach are demonstrated through a series of representative numerical experiments.
Problem
Research questions and friction points this paper is trying to address.
dual-network porous media
fluid flow
double porosity/permeability
inverse analysis
computational framework
Innovation
Methods, ideas, or system contributions that make the work stand out.
Physics-Informed Neural Networks
Dual-Porosity Permeability
Adaptive Weighting
Mesh-Free Modeling
Inverse Parameter Identification
🔎 Similar Papers
No similar papers found.
