A deep learning perspective on predicting permeability in porous media from network modeling to direct simulation
- PDF / 3,268,237 Bytes
- 16 Pages / 595.224 x 790.955 pts Page_size
- 16 Downloads / 200 Views
ORIGINAL PAPER
A deep learning perspective on predicting permeability in porous media from network modeling to direct simulation Moussa Tembely1
· Ali M. AlSumaiti1 · Waleed Alameri1
Received: 19 June 2019 / Accepted: 30 March 2020 © Springer Nature Switzerland AG 2020
Abstract Predicting the petrophysical properties of rock samples using micro-CT images has gained significant attention recently. However, an accurate and an efficient numerical tool is still lacking. After investigating three numerical techniques, (i) pore network modeling (PNM), (ii) the finite volume method (FVM), and (iii) the lattice Boltzmann method (LBM), a workflow based on machine learning is established for fast and accurate prediction of permeability directly from 3D micro-CT images. We use more than 1100 samples scanned at high resolution and extract the relevant features from these samples for use in a supervised learning algorithm. The approach takes advantage of the efficient computation provided by PNM and the accuracy of the LBM to quickly and accurately estimate rock permeability. The relevant features derived from PNM and image analysis are fed into a supervised machine learning model and a deep neural network to compute the permeability in an end-to-end regression scheme. Within a supervised learning framework, machine and deep learning algorithms based on linear regression, gradient boosting, and physics-informed convolutional neural networks (CNNs) are applied to predict the petrophysical properties of porous rock from 3D micro-CT images. We have performed the sensitivity analysis on the feature importance, hyperparameters, and different learning algorithms to make a prediction. Values of R 2 scores up to 88% and 91% are achieved using machine learning regression models and the deep learning approach, respectively. Remarkably, a significant gain in computation time—approximately 3 orders of magnitude—is achieved by applied machine learning compared with the LBM. Finally, the study highlights the critical role played by feature engineering in predicting petrophysical properties using deep learning. Keywords Digital rock physics · Porous media · Finite volume method · Lattice Boltzmann method · Pore network modeling · Tensor flow · Machine learning · Deep learning
1 Introduction Accurate and fast computation of the properties of subsurface porous media properties is required in many applications, including contaminant cleanup, the oil and gas industry, capturing subsurface CO2 flow, and gas diffusion layer (GDL) in fuel cells. However, characterizing complex rock such as carbonate remains very challenging due to the intrinsic heterogeneities occurring at all scales of observation and measurement [1]. One of the most important petrophysical properties of reservoir rock is the permeability, which is a
Moussa Tembely
[email protected],[email protected] 1
Department of Petroleum Engineering, Khalifa University, Abu Dhabi, UAE
function of the complex microstructure of the rock, fluid properties (density, visc
Data Loading...
