Prediction of two-phase flow properties for digital sandstones using 3D convolutional neural networks

• Published in: Advances in water resources Vol. 176; p. 104442
• Main Authors: Telvari, Saeed, Sayyafzadeh, Mohammad, Siavashi, Javad, Sharifi, Mohammad
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.06.2023
• Subjects: Capillary pressure; carbon dioxide; contact angle; Convolutional neural networks; data collection; fuels; groundwater; Multiphase flow; neural networks; oils; permeability; Pore-scale simulation; prediction; Relative permeability; remediation; Capillary pressure; Pore-scale simulation; Relative permeability; Multiphase flow; Convolutional neural networks
• ISSN: 0309-1708; 1872-9657
• DOI: 10.1016/j.advwatres.2023.104442

Multiphase fluid flow within porous media is of great importance in a wide range of environmental and industrial fields, such as CO2 sequestration, geothermal systems, fuel cells, enhanced oil recovery, and groundwater remediation. Pore-scale modeling is a promising tool to estimate macroscopic multiphase flow properties from micro-scale images of porous materials; however, it is a complex, time-consuming procedure and would be highly resource-intensive in the case of direct numerical simulation. We present a framework that consists of (1) extraction of sub-samples from rock images, (2) computation of relative permeability and capillary pressure from two-phase pore network modeling with respect to their contact angle and interfacial tensions, (3) training a convolutional neural network (CNN), and (4) validation with unseen datasets and parameters. 500 sub-samples of grayscale and binary types are extracted from images of 12 different sandstones. Relative permeability, capillary pressure, and residual saturation of binary sub-samples are computed from two-phase fluid flow simulation in their representative pore network models The proposed CNN model is trained with grayscale images, eliminating the need for image processing. The results demonstrate a good agreement between CNN predictions and simulation results, and the computational time was reduced by several orders of magnitude. •Proposed model predicts two-phase properties with promising accuracy and efficiency.•The network enables direct predictions from raw, unprocessed images of rock samples.•CNN predicts permeability and capillary pressure based on contact angle and IFT.