Efficient Deep Learning Techniques for Multiphase Flow Simulation in Heterogeneous Porous Media
Authors:
Preprint
Abstract
We present efficient deep learning techniques for approximating flow and transport equations for both single phase and two-phase flow problems. The proposed methods take advantages of the sparsity structures in the underlying discrete systems and can be served as efficient alternatives to the system solvers at the full order. In particular, for the flow problem, we design a network with convolutional and locally connected layers to perform model reductions. Moreover, we employ a custom loss function to impose local mass conservation constraints. This helps to preserve the physical property of velocity solution which we are interested in learning. For the saturation problem, we propose a residual type of network to approximate the dynamics. Our main contribution here is the design of custom sparsely connected layers which take into account the inherent sparse interaction between the input and output. After training, the approximated feed-forward map can be applied iteratively to predict solutions in the long range. Our trained networks, especially in two-phase flow where the maps are nonlinear, show their great potential in accurately approximating the underlying physical system and improvement in computational efficiency. Some numerical experiments are performed and discussed to demonstrate the performance of our proposed techniques.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- Deep global model reduction learning in porous media flow simulationComputational Geosciences, 2019
- The Deep Ritz Method: A Deep Learning-Based Numerical Algorithm for Solving Variational ProblemsCommunications in Mathematics and Statistics, 2018
- A conservative local multiscale model reduction technique for Stokes flows in heterogeneous perforated domainsJournal of Computational and Applied Mathematics, 2017
- Generalized multiscale finite element method for elasticity equationsGEM - International Journal on Geomathematics, 2014
- Adaptive reduced basis finite element heterogeneous multiscale methodComputer Methods in Applied Mechanics and Engineering, 2013
- The heterogeneous multiscale finite element method for elliptic homogenization problems in perforated domainsNumerische Mathematik, 2009
- Mathematical homogenization of nonperiodic heterogeneous media subjected to large deformation transient loadingInternational Journal for Numerical Methods in Engineering, 2008
- Metric‐based upscalingCommunications on Pure and Applied Mathematics, 2006
- Space–time multiscale model for wave propagation in heterogeneous mediaComputer Methods in Applied Mechanics and Engineering, 2004
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991