Seeing Permeability From Images: Fast Prediction with Convolutional Neural Networks

Abstract

Fast prediction of permeability directly from images enabled by image recognition neural networks is a novel pore-scale modeling method that has a great potential. This article presents a framework that includes (1) generation of porous media samples, (2) computation of permeability via fluid dynamics simulations, (3) training of convolutional neural networks (CNN) with simulated data, and (4) validations against simulations. Comparison of machine learning results and the ground truths suggests excellent predictive performance across a wide range of porosities and pore geometries, especially for those with dilated pores. Owning to such heterogeneity, the permeability cannot be estimated using the conventional Kozeny-Carman approach. Computational time was reduced by several orders of magnitude compared to fluid dynamic simulations. We found that, by including physical parameters that are known to affect permeability into the neural network, the physics-informed CNN generated better results than regular CNN, however improvements vary with implemented heterogeneity.

arXiv comment17 pages, 8 figures

References in corpus (7)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• A Physics Informed Machine Learning Approach for Reconstructing Reynolds Stress Modeling Discrepancies Based on DNS Data
• Reconstruction of three-dimensional porous media using generative adversarial neural networks
• A Comprehensive Physics-Informed Machine Learning Framework for Predictive Turbulence Modeling
• Physics-Informed Machine Learning Approach for Augmenting Turbulence Models: A Comprehensive Framework
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• Data-Driven, Physics-Based Feature Extraction from Fluid Flow Fields

Cited by in corpus (13)

• Predicting Porosity, Permeability, and Tortuosity of Porous Media from Images by Deep Learning
• DeePore: a deep learning workflow for rapid and comprehensive characterization of porous materials
• A Critical Review of Physics-Informed Machine Learning Applications in Subsurface Energy Systems
• Predicting permeability via statistical learning on higher-order microstructural information
• Point-Cloud Deep Learning of Porous Media for Permeability Prediction
• Deep learning for diffusion in porous media
• A Computationally Efficient Hybrid Neural Network Architecture for Porous Media: Integrating Convolutional and Graph Neural Networks for Improved Property Predictions
• Morphology Decoder: A Machine Learning Guided 3D Vision Quantifying Heterogenous Rock Permeability for Planetary Surveillance and Robotic Functions
• Equivariant geometric learning for digital rock physics: estimating formation factor and effective permeability tensors from Morse graph
• Predicting Effective Diffusivity of Porous Media from Images by Deep Learning
• Transferable 3D Convolutional Neural Networks for Elastic Constants Prediction in Nanoporous Metals
• Recurrent Neural Network for End-to-End Modeling of Laminar-Turbulent Transition
• Deep Convolutional Neural Networks Predict Elasticity Tensors and their Bounds in Homogenization