USING PHYSICS-INFORMED NEURAL NETWORKS TO SOLVE FOR PERMEABILITY FIELD UNDER TWO-PHASE FLOW IN HETEROGENEOUS POROUS MEDIA

被引:0
作者
Yang, Mingyuan [1 ]
Foster, John T. [1 ]
机构
[1] Univ Texas Austin, Dept Petr & Geosyst Engn, Austin, TX 78712 USA
来源
JOURNAL OF MACHINE LEARNING FOR MODELING AND COMPUTING | 2023年 / 4卷 / 01期
关键词
physics-informed neural networks; two phase flow; inverse problem; dynamics prediction;
D O I
10.1615/JMachLearnModelComput.2023046921
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Physics-informed neural networks (PINNs) have recently been applied to a wide range of computational physical problems. In this paper, we use PINNs to solve an inverse two-phase flow problem in heterogeneous porous media where only sparse direct and indirect measurements are available. The forward two-phase flow problem is governed by a coupled system of partial differential equations (PDEs) with initial and boundary conditions. As for inverse problems, the solutions are assumed to be known at scattered locations but some coefficients or variable functions in the PDEs are missing or incomplete. The idea is to train multiple neural networks representing the solutions and the unknown variable function at the same time such that both the underlying physical laws and the measurements can be honored. The numerical results show that our proposed method is able to recover the incomplete permeability field in different scenarios. Moreover, we show that the method can be used to forecast the future dynamics with the same format of loss function formulation. In addition, we employ a neural network structure inspired by the deep operator networks (DeepONets) to represent the solutions which can potentially shorten the time of the training process.
引用
收藏
页码:1 / 19
页数:19
相关论文
共 21 条
[1]  
Alnæs MS, 2015, V3, P9, DOI [10.11588/ans.2015.100.20553, DOI 10.11588/ANS.2015.100.20553, 10.11588/ans.2015.100.20553]
[2]   A unified deep artificial neural network approach to partial differential equations in complex geometries [J].
Berg, Jens ;
Nystrom, Kaj .
NEUROCOMPUTING, 2018, 317 :28-41
[3]  
Fraces C.G., 2020, ARXIV
[4]  
Fuks O, 2020, J MACH LEARN MODEL C, V1, P19, DOI [10.1615/jmachlearnmodelcomput.2020033905, 10.1615/JMachLearnModelComput.2020033905, DOI 10.1615/JMACHLEARNMODELCOMPUT.2020033905]
[5]   Transfer learning enhanced physics informed neural network for phase-field modeling of fracture [J].
Goswami, Somdatta ;
Anitescu, Cosmin ;
Chakraborty, Souvik ;
Rabczuk, Timon .
THEORETICAL AND APPLIED FRACTURE MECHANICS, 2020, 106
[6]  
Haghighat E., 2020, ARXIV
[7]   Physics-informed neural networks for multiphysics data assimilation with application to subsurface transport [J].
He, QiZhi ;
Barajas-Solano, David ;
Tartakovsky, Guzel ;
Tartakovsky, Alexandre M. .
ADVANCES IN WATER RESOURCES, 2020, 141
[8]  
Kharazmi E., 2020, ARXIV
[9]  
Paszke Adam., 2017, NIPS
[10]  
Raissi M, 2018, J MACH LEARN RES, V19