Simulation of multiphase flow in porous media is crucial for the effective management of subsurface energy and environment related activities. The numerical simulators used for modeling such processes rely on spatial and temporal discretization of the governing partial-differential equations (PDEs) into algebraic systems via numerical methods. These simulators usually require dedicated software development and maintenance, and suffer low efficiency from a runtime and memory standpoint. Therefore, developing cost-effective, data-driven models can become a practical choice since deep learning approaches are considered to be universal approximations. In this paper, we describe a gradient-based deep neural network (GDNN) constrained by the physics related to multiphase flow in porous media. We tackle the nonlinearity of flow in porous media induced by rock heterogeneity, fluid properties and fluid-rock interactions by decomposing the nonlinear PDEs into a dictionary of elementary differential operators. We use a combination of operators to handle rock spatial heterogeneity and fluid flow by advection. Since the augmented differential operators are inherently related to the physics of fluid flow, we treat them as first principles prior knowledge to regularize the GDNN training. We use the example of pressure management at geologic CO2 storage sites, where CO2 is injected in saline aquifers and brine is produced, and apply GDNN to construct a predictive model that is trained from physics-based simulation data and emulates the physics process. We demonstrate that GDNN can effectively predict the nonlinear patterns of subsurface responses including the temporal-spatial evolution of the pressure and saturation plumes. GDNN has great potential to tackle challenging problems that are governed by highly nonlinear physics and enables development of data-driven models with higher fidelity.
翻译:在多孔介质中模拟多相流对于有效管理地下能量和环境相关活动至关重要。 用于模拟这些过程的数字模拟器取决于通过数字方法将调节的局部偏差方程式(PDEs)在空间和时间上分解成代数系统中的代数系统。 这些模拟器通常需要专门的软件开发和维护,并且从运行时间和记忆角度看效率较低。 因此, 开发具有成本效益的、 数据驱动的模型可以成为一种实用的选择, 因为深层学习方法被认为是普遍的近似值。 在本文中, 我们描述了一个基于梯度的深层神经网络(GDNNN)受与多孔介质流多相流有关的物理模型限制。 我们通过将非线性PDDs模型分解到基本差操作者的字典中,将非线性媒体流的无线性流动纳入代数中。 我们使用操作者组合处理岩石空间模型的偏差和液流反应。 由于扩大的轨迹与液流的物理模拟DND(GND)的物理模型有内在联系, 我们把它们视为在GNNF2的不透明数据存储过程中的第一个原则, 。 我们用GNFSD(G) 和G- drodealalal 的精化数据是用来在G- creal 的模拟中,在G- creal- a 数据管理中,我们用GND- brodeal- a 的模拟的模型中, 我们用一个高压数据是用来在G- creal- a 。