A physics-constrained deep learning model for simulating multiphase flow in 3D heterogeneous porous media
نویسندگان
چکیده
Physics-based simulators for multiphase flow in porous media emulate nonlinear processes with coupled physics, and usually require extensive computational resources software development, maintenance simulation execution. As a result, huge demand exists fast modeling of wide range subsurface applications including geological CO2 sequestration, hydrocarbon recovery geothermal energy extraction. In this work, an efficient physics-constrained deep learning model is developed solving 3-Dimensional (3D) heterogeneous media. The fully leverages the spatial topology predictive capability convolutional neural networks, specifically U-Net successive contracting expansive steps, continuity-based smoother to predict responses that need continuity. Furthermore, transient regions are penalized steer training process such can accurately capture these regions. takes inputs properties media, fluid well controls, predicts temporal-spatial evolution state variables (pressure saturation). While maintaining continuity flow, 3D domain decomposed into 2D images reducing cost, decomposition results increased number data samples better efficiency. Additionally, surrogate separately constructed as postprocessor calculate rate based on predictions from model. We use example injection saline aquifers, apply trained physics-based emulates physics process. performs prediction speedup ? 1400 times compared simulations, average temporal errors predicted pressure saturation plumes 0.27% 0.099% respectively. water production efficiently by rate, mean error less than 5%. Therefore, its unique scheme cope fidelity become computationally demanding inverse problems or other processes.
منابع مشابه
Multiscale Model Reduction Methods for Flow in Heterogeneous Porous Media
In this paper we provide a general framework for model reduction methods applied to fluid flow in porous media. Using reduced basis and numerical homogenization techniques we show that the complexity of the numerical approximation of Stokes flow in heterogeneous media can be drastically reduced. The use of such a computational framework is illustrated at several model problems such as two and t...
متن کاملIterative Multiscale Finite Volume Method for Multiphase Flow in Porous Media with Complex Physics
In this thesis, the multiscale finite-volume (MSFV) method for the solution of elliptic problems is extended to an efficient iterative algorithm that converges to the fine-scale numerical solution. The localization errors in the MSFV method are systematically reduced by updating the local boundary conditions with global information. This iterative multiscale finite-volume (i-MSFV) method allows...
متن کاملAlgebraic Dynamic Multilevel (ADM) Method for Immiscible Multiphase Flow in Heterogeneous Porous Media with Capillarity
متن کامل
Stochastic Finite Element Analysis for Multiphase Flow in Heterogeneous Porous Media
This study is concerned with developing a two-dimensional multiphase model that simulates the movement of NAPL in heterogeneous aquifers. Heterogeneity is dealt with in a probabilistic sense by modeling the intrinsic permeability of the porous medium as a stochastic process. The deterministic nite element method is used to spatially discretize the multiphase ow equations. The intrinsic permeabi...
متن کاملFlow in porous media pore-network models and multiphase flow
In the last 3 years there has been a huge increase in the use of pore-scale modeling to study multiphase flow and transport in porous media. Starting from single pore models of fluid arrangements, computations of relative permeability, interfacial area, dissolution rate and many other physical properties have been made. Combined with a realistic description of the pore space, predictive modelin...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Fuel
سال: 2022
ISSN: ['0016-2361', '1873-7153']
DOI: https://doi.org/10.1016/j.fuel.2021.122693