Point-Cloud Deep Learning of Porous Media for Permeability Prediction

  title={Point-Cloud Deep Learning of Porous Media for Permeability Prediction},
  author={Ali Kashefi and Tapan Mukerji},
We propose a novel deep learning framework for predicting permeability of porous media from their digital images. Unlike convolutional neural networks, instead of feeding the whole image volume as inputs to the network, we model the boundary between solid matrix and pore spaces as point clouds and feed them as inputs to a neural network based on the PointNet architecture. This approach overcomes the challenge of memory restriction of graphics processing units and its consequences on the choice… Expand


Seeing permeability from images: fast prediction with convolutional neural networks
It is 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. Expand
A deep learning perspective on predicting permeability in porous media from network modeling to direct simulation
A workflow based on machine learning is established for fast and accurate prediction of permeability directly from 3D micro-CT images and highlights the critical role played by feature engineering in predicting petrophysical properties using deep learning. Expand
Rapid estimation of permeability from digital rock using 3D convolutional neural network
3D CNN-based approach for rapidly estimating permeability in anisotropic rock provides an alternative way to calculate permeability with low computing cost, and has the potential to be extended to the estimation of relative permeability and other properties of rocks. Expand
Predicting Effective Diffusivity of Porous Media from Images by Deep Learning
The application of machine learning methods for predicting the effective diffusivity (De) of two-dimensional porous media from images of their structures suggests that deep learning augmented by field knowledge can be a powerful technique for predicted the transport properties of porous media. Expand
ML-LBM: Machine Learning Aided Flow Simulation in Porous Media
An integrated method combining predictions of fluid flow (fast, limited accuracy) with direct flow simulation (slow, high accuracy) is outlined and using Deep Learning predictions to accelerate flow simulation to steady state in complex pore structures shows promise as a technique push the boundaries fluid flow modelling. Expand
Machine learning for predicting properties of porous media from 2d X-ray images
The results from testing the proposed CNN framework are promising as the relative error in determination of porosity, surface area and average pore size is less than 6% when the model is trained with binary images and less than 7% when greyscale images are used. Expand
Image-based velocity estimation of rock using Convolutional Neural Networks
The estimated properties, in comparison with the computational results, indicate that CNNs perform outstandingly in predicting the physical parameters of rock without conducting any time-demanding forward modeling if enough input data are provided. Expand
Digital core repository coupled with machine learning as a tool to classify and assess petrophysical rock properties
To make efficient use of image-based rock physics workflow, it is necessary to optimize different criteria, among which: quantity, representativeness, size and resolution. Advances in artificialExpand
Unsupervised Representation Learning with Deep Convolutional Neural Network for Remote Sensing Images
This work investigates a real-world motivated sparsity based unsupervised deep CNN learning method that is used for the remote sensing image representation and scenes classification and demonstrates that the developed algorithm obtained satisfactory results compared with the recent methods. Expand
Fast flow field prediction over airfoils using deep learning approach
In this paper, a data driven approach is presented for the prediction of incompressible laminar steady flow field over airfoils based on the combination of deep Convolutional Neural Network (CNN) andExpand