Efficient uncertainty quantification for dynamic subsurface flow with surrogate by Theory-guided Neural Network

Wang，Nanzhe1; Chang，Haibin1; Zhang，Dongxiao2,3,4

2021

10.1016/j.cma.2020.113492

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING   影响因子和分区

0045-7825

1879-2138

Subsurface flow problems usually involve some degree of uncertainty. Consequently, uncertainty quantification is commonly necessary for subsurface flow prediction. In this work, we propose a methodology for efficient uncertainty quantification for dynamic subsurface flow with a surrogate constructed by the Theory-guided Neural Network (TgNN). The TgNN here is specially designed for problems with stochastic parameters. In the TgNN, stochastic parameters, time and location comprise the input of the neural network, while the quantity of interest is the output. The neural network is trained with available simulation data, while being simultaneously guided by theory (e.g., the governing equation, boundary conditions, initial conditions, etc.) of the underlying problem. The trained neural network can predict solutions of subsurface flow problems with new stochastic parameters. With the TgNN surrogate, the Monte Carlo (MC) method can be efficiently implemented for uncertainty quantification. The proposed methodology is evaluated with two-dimensional dynamic saturated flow problems in porous medium. Numerical results show that the TgNN based surrogate can significantly improve the efficiency of uncertainty quantification tasks compared with simulation based implementation. Further investigations regarding stochastic fields with smaller correlation length, larger variance, changing boundary values and out-of-distribution variances are performed, and satisfactory results are obtained. (C) 2020 The Author(s). Published by Elsevier B.V.

Theory-guided Neural Network Surrogate modeling Subsurface flow Uncertainty quantification

SCI ; EI

英语

其他

National Natural Science Foundation of China[51520105005,"U1663208"] ; National Science and Technology Major Project of China["2017ZX05009-005","2017ZX05049-003"]

Engineering ; Mathematics ; Mechanics

Engineering, Multidisciplinary ; Mathematics, Interdisciplinary Applications ; Mechanics

WOS:000600288300006

ELSEVIER SCIENCE SA

20204409433635

Uncertainty analysis ; Porous materials ; Monte Carlo methods

Control Systems:731.1 ; Probability Theory:922.1 ; Mathematical Statistics:922.2 ; Materials Science:951 ; Systems Science:961

COMPUTER SCIENCE

Web of Science

1.BIC-ESAT,ERE,and SKLTCS,College of Engineering,Peking University,Beijing,100871,China
2.Guangdong Provincial Key Laboratory of Soil and Groundwater Pollution Control,School of Environmental Science and Engineering,Southern University of Science and Technology,Shenzhen,518055,China
3.State Environmental Protection Key Laboratory of Integrated Surface Water–Groundwater Pollution Control,School of Environmental Science and Engineering,Southern University of Science and Technology,Shenzhen,518055,China
4.Intelligent Energy Lab,Peng Cheng Laboratory,Shenzhen,518000,China

Wang，Nanzhe,Chang，Haibin,Zhang，Dongxiao. Efficient uncertainty quantification for dynamic subsurface flow with surrogate by Theory-guided Neural Network[J]. COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING,2021,373.

Wang，Nanzhe,Chang，Haibin,&Zhang，Dongxiao.(2021).Efficient uncertainty quantification for dynamic subsurface flow with surrogate by Theory-guided Neural Network.COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING,373.

Wang，Nanzhe,et al."Efficient uncertainty quantification for dynamic subsurface flow with surrogate by Theory-guided Neural Network".COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 373(2021).