File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.jcp.2019.108968
- Scopus: eid_2-s2.0-85073829229
- WOS: WOS:000501350300007
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Efficient deep learning techniques for multiphase flow simulation in heterogeneous porousc media
Title | Efficient deep learning techniques for multiphase flow simulation in heterogeneous porousc media |
---|---|
Authors | |
Keywords | Multiphase flow Porous media Neural network Flow and transport Machine learning Deep learning |
Issue Date | 2020 |
Citation | Journal of Computational Physics, 2020, v. 401, article no. 108968 How to Cite? |
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. |
Persistent Identifier | http://hdl.handle.net/10722/303628 |
ISSN | 2023 Impact Factor: 3.8 2023 SCImago Journal Rankings: 1.679 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, Yating | - |
dc.contributor.author | Lin, Guang | - |
dc.date.accessioned | 2021-09-15T08:25:42Z | - |
dc.date.available | 2021-09-15T08:25:42Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | Journal of Computational Physics, 2020, v. 401, article no. 108968 | - |
dc.identifier.issn | 0021-9991 | - |
dc.identifier.uri | http://hdl.handle.net/10722/303628 | - |
dc.description.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. | - |
dc.language | eng | - |
dc.relation.ispartof | Journal of Computational Physics | - |
dc.subject | Multiphase flow | - |
dc.subject | Porous media | - |
dc.subject | Neural network | - |
dc.subject | Flow and transport | - |
dc.subject | Machine learning | - |
dc.subject | Deep learning | - |
dc.title | Efficient deep learning techniques for multiphase flow simulation in heterogeneous porousc media | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.jcp.2019.108968 | - |
dc.identifier.scopus | eid_2-s2.0-85073829229 | - |
dc.identifier.volume | 401 | - |
dc.identifier.spage | article no. 108968 | - |
dc.identifier.epage | article no. 108968 | - |
dc.identifier.eissn | 1090-2716 | - |
dc.identifier.isi | WOS:000501350300007 | - |