Uncertainty quantification of two-phase flow in porous media via the Coupled-TgNN surrogate model

Li, Jian1; Zhang, Dongxiao2; He, Tianhao3; Zheng, Qiang4

2023-02-01

10.1016/j.geoen.2022.211368

GEOENERGY SCIENCE AND ENGINEERING   影响因子和分区

2949-8929

2949-8910

The uncertainty quantification (UQ) of subsurface two-phase flow usually requires numerous executions of forward simulations under varying conditions. In this work, a novel coupled theory-guided neural network (TgNN) based surrogate model is built to facilitate computation efficiency under the premise of satisfactory accuracy. The core notion of this proposed method is to bridge two separate blocks on top of an overall network. They underlie the TgNN model in a coupled form, which reflects the coupling nature of pressure and water saturation in the two-phase flow equation. The TgNN model not only relies on labeled data, but also incorporates underlying scientific theory and experiential rules (e.g., governing equations, stochastic parameter fields, boundary and initial conditions, well conditions, and expert knowledge) as additional components into the loss function. The performance of the TgNN-based surrogate model for two-phase flow problems is tested by different numbers of labeled data and collocation points, as well as the existence of data noise. The proposed TgNN-based surrogate model offers an effective way to solve the coupled nonlinear two-phase flow problem, and shows good accuracy and strong robustness when compared with the purely data-driven surrogate model. By combining the accurate TgNN-based surrogate model with the Monte Carlo method, UQ tasks can be performed at a minimum cost to evaluate statistical quantities. Since the heterogeneity of the random fields strongly impacts the results of the surrogate model, corresponding variance and correlation length are added to the input of the neural network to maintain its predictive capacity. In addition, several more complicated scenarios are also considered, including dynamically changing well conditions and dynamically changing variance of random fields. The results show that the TgNN-based surrogate model exhibits satisfactory accuracy, stability, and efficiency in the UQ problem of subsurface two-phase flow.

Coupled theory -guided neural network Uncertainty quantification Surrogate model Two-phase flow

SCI ; EI

英语

通讯

Shenzhen Key Laboratory of Natural Gas Hydrates[ZDSYS20200421111201738] ; China Postdoctoral Science Foundation[2020M682830]

Energy & Fuels ; Engineering

Energy & Fuels ; Engineering, Petroleum

WOS:000972998200001

ELSEVIER

20232114134283

Computation theory ; Efficiency ; Monte Carlo methods ; Porous materials ; Stochastic models ; Stochastic systems ; Uncertainty analysis

Fluid Flow, General:631.1 ; Computer Theory, Includes Formal Logic, Automata Theory, Switching Theory, Programming Theory:721.1 ; Control Systems:731.1 ; Production Engineering:913.1 ; Probability Theory:922.1 ; Mathematical Statistics:922.2 ; Materials Science:951 ; Systems Science:961

Web of Science

1.China Univ Petr East China, Dongying, Peoples R China
2.Southern Univ Sci & Technol, Shenzhen Key Lab Nat Gas Hydrates, Shenzhen 518055, Peoples R China
3.Peking Univ, Beijing, Peoples R China
4.Peng Cheng Lab, Shenzhen, Peoples R China

Li, Jian,Zhang, Dongxiao,He, Tianhao,et al. Uncertainty quantification of two-phase flow in porous media via the Coupled-TgNN surrogate model[J]. GEOENERGY SCIENCE AND ENGINEERING,2023,221.

Li, Jian,Zhang, Dongxiao,He, Tianhao,&Zheng, Qiang.(2023).Uncertainty quantification of two-phase flow in porous media via the Coupled-TgNN surrogate model.GEOENERGY SCIENCE AND ENGINEERING,221.

Li, Jian,et al."Uncertainty quantification of two-phase flow in porous media via the Coupled-TgNN surrogate model".GEOENERGY SCIENCE AND ENGINEERING 221(2023).