Fast Prediction of Immiscible Two-Phase Displacements in Heterogeneous Porous Media with Convolutional Neural Network

Fast Prediction of Immiscible Two-Phase Displacements in Heterogeneous Porous Media with Convolutional Neural Network

Year:    2021

Author:    Wei Feng, Haibo Huang

Advances in Applied Mathematics and Mechanics, Vol. 13 (2021), Iss. 1 : pp. 140–162

Abstract

A convolutional neural network is developed for rapidly predicting multiphase flow in heterogeneous porous media. Some direct numerical methods can acquire accurate results of multiphase flow in porous media. However, once the geometry of the porous media changes, it takes much computational time to perform a new simulation. Here, a deep neural network model in the field of semantic segmentation is developed. It takes the two-dimensional microstructure of heterogeneous porous media as inputs and is able to predict corresponding multiphase flow fields (pressure and saturation fields). Compared to the direct lattice Boltzmann simulations, the inference time on new geometry of porous media can be reduced by several orders of magnitude. Our results show that the machine learning method is a good prediction tool in a wide range of porosity and heterogeneity. Besides, to better understand the inherent process, a visible explanation is presented on what our neural networks have learned.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/aamm.OA-2019-0377

Advances in Applied Mathematics and Mechanics, Vol. 13 (2021), Iss. 1 : pp. 140–162

Published online:    2021-01

AMS Subject Headings:    Global Science Press

Copyright:    COPYRIGHT: © Global Science Press

Pages:    23

Keywords:    Porous media multiphase flow convolutional neural network porosity sorting.

Author Details

Wei Feng

Haibo Huang

  1. Estimating Residual Oil Saturation in Carbonate Rocks: A Combined Approach of Direct Simulation and Data-Driven Analysis

    Rizk, A. S. | Tembely, M. | AlAmeri, W. | Al-Shalabi, E. W. | Farmanov, R. | Markovic, S.

    SPE Journal, Vol. 29 (2024), Iss. 10 P.5617

    https://doi.org/10.2118/221498-PA [Citations: 0]
  2. Modified UNet with attention gate and dense skip connection for flow field information prediction with porous media

    Yu, Yang | Chen, Sheng | Wei, Heng

    Flow Measurement and Instrumentation, Vol. 89 (2023), Iss. P.102300

    https://doi.org/10.1016/j.flowmeasinst.2022.102300 [Citations: 12]
  3. Fast prediction method of displacement front in heterogeneous porous media using deep learning and orthogonal design

    Zhao, Dong | Hou, Jian | Wei, Bei | Liu, Haihu | Du, Qingjun | Zhang, Yang | Sun, Zezheng

    Physics of Fluids, Vol. 35 (2023), Iss. 8

    https://doi.org/10.1063/5.0160984 [Citations: 1]
  4. Residual Oil Saturation Estimation from Carbonate Rock Images Based on Direct Simulation and Machine Learning

    Rizk, Ahmed Samir | Tembely, Moussa | AlAmeri, Waleed | Al-Shalabi, Emad W.

    Day 3 Wed, February 23, 2022, (2022),

    https://doi.org/10.2523/IPTC-22096-MS [Citations: 0]
  5. Predicting elastic modulus of porous La0.6Sr0.4Co0.2Fe0.8O3-δ cathodes from microstructures via FEM and deep learning

    Liu, Xuhao | Yan, Zilin | Zhong, Zheng

    International Journal of Hydrogen Energy, Vol. 46 (2021), Iss. 42 P.22079

    https://doi.org/10.1016/j.ijhydene.2021.04.033 [Citations: 22]
  6. Deep learning for pore-scale two-phase flow: Modelling drainage in realistic porous media

    ASADOLAHPOUR, Seyed Reza | JIANG, Zeyun | LEWIS, Helen | MIN, Chao

    Petroleum Exploration and Development, Vol. 51 (2024), Iss. 5 P.1301

    https://doi.org/10.1016/S1876-3804(25)60542-8 [Citations: 0]
  7. Predicting gas diffusion layer flow information in proton exchange membrane fuel cells from cross-sectional data using deep learning methods

    Yu, Yang | Chen, Sheng | Wu, Yuanhao

    Energy, Vol. 282 (2023), Iss. P.128778

    https://doi.org/10.1016/j.energy.2023.128778 [Citations: 2]