Surrogate and inverse modeling for two-phase flow in porous media via theory-guided convolutional neural network

Wang，Nanzhe1; Chang，Haibin2; Zhang，Dongxiao3,4

2022-10-01

10.1016/j.jcp.2022.111419

JOURNAL OF COMPUTATIONAL PHYSICS   Impact Factor & Quartile

0021-9991

1090-2716

The theory-guided convolutional neural network (TgCNN) framework, which can incorporate discretized governing equation residuals into the training of convolutional neural networks (CNNs), is extended to two-phase porous media flow problems in this work. The two principal variables of the considered problem, pressure and saturation, are approximated simultaneously with two CNNs, respectively. Pressure and saturation are coupled with each other in the governing equations, and thus the two networks are also mutually conditioned in the training process by the discretized governing equations, which also increases the difficulty of model training. The coupled and discretized equations can provide valuable information in the training process. With the assistance of theory-guidance, the TgCNN surrogates can achieve better accuracy than ordinary CNN surrogates in two-phase flow problems. Moreover, a piecewise training strategy is proposed for the scenario with varying well controls, in which the TgCNN surrogates are constructed for different segments on the time dimension and stacked together to predict solutions for the whole time-span. For scenarios with larger variance of the formation property field, the TgCNN surrogates can also achieve satisfactory performance. The constructed TgCNN surrogates are further used for inversion of permeability fields by combining them with the iterative ensemble smoother (IES) algorithm, and sufficient inversion accuracy is obtained with improved efficiency.

Inverse modeling Surrogate modeling Theory-guided convolutional neural network Two-phase flow

EI ; SCI

English

Corresponding

Shenzhen Key Laboratory of Natural Gas Hydrates[ZDSYS20200421111201738]

Computer Science ; Physics

Computer Science, Interdisciplinary Applications ; Physics, Mathematical

WOS:000885956800002

ACADEMIC PRESS INC ELSEVIER SCIENCE

20222812351914

Convolution ; Convolutional neural networks ; Inverse problems ; Iterative methods ; Porous materials

Fluid Flow, General:631.1 ; Information Theory and Signal Processing:716.1 ; Numerical Methods:921.6 ; Materials Science:951

PHYSICS

2-s2.0-85133738819

Scopus

1.BIC-ESAT,ERE,and SKLTCS,College of Engineering,Peking University,Beijing,100871,China
2.School of Energy and Mining Engineering,China University of Mining and Technology (Beijing),Beijing,100083,China
3.National Center for Applied Mathematics Shenzhen (NCAMS),Southern University of Science and Technology,Shenzhen,Guangdong,518055,China
4.Department of Mathematics and Theories,Peng Cheng Laboratory,Shenzhen,Guangdong,518000,China

Wang，Nanzhe,Chang，Haibin,Zhang，Dongxiao. Surrogate and inverse modeling for two-phase flow in porous media via theory-guided convolutional neural network[J]. JOURNAL OF COMPUTATIONAL PHYSICS,2022,466.

Wang，Nanzhe,Chang，Haibin,&Zhang，Dongxiao.(2022).Surrogate and inverse modeling for two-phase flow in porous media via theory-guided convolutional neural network.JOURNAL OF COMPUTATIONAL PHYSICS,466.

Wang，Nanzhe,et al."Surrogate and inverse modeling for two-phase flow in porous media via theory-guided convolutional neural network".JOURNAL OF COMPUTATIONAL PHYSICS 466(2022).