Recent Advances in Reservoir Simulation

Geological CO₂ sequestration (GCS) has been proposed as an effective approach to mitigate carbon emissions in the atmosphere. Uncertainty and sensitivity analysis of the fate of CO₂ dynamics and storage are essential aspects of large-scale reservoir simulations. This work presents a rigorous machine learning-assisted (ML) workflow for the uncertainty and global sensitivity analysis of CO₂ storage prediction in deep saline aquifers. The proposed workflow comprises three main steps: The first step concerns dataset generation, in which we identify the uncertainty parameters impacting CO₂ flow and transport and then determine their corresponding ranges and distributions. The training data samples are generated by combining the Latin Hypercube Sampling (LHS) technique with high-resolution simulations. The second step involves ML model development based on a data-driven ML model, which is generated to map the nonlinear relationship between the input parameters and corresponding output interests from the previous step. We show that using Bayesian optimization significantly accelerates the tuning process of hyper-parameters, which is vastly superior to a traditional trial–error analysis. In the third step, uncertainty and global sensitivity analysis are performed using Monte Carlo simulations applied to the optimized surrogate. This step is performed to explore the time-dependent uncertainty propagation of model outputs. The key uncertainty parameters are then identified by calculating the Sobol indices based on the global sensitivity analysis. The proposed workflow is accurate and efficient and could be readily implemented in field-scale CO₂ sequestration in deep saline aquifers. Full article

We develop a multiscale simulation strategy, namely, algebraic dynamic multilevel (ADM) method, for simulation of fluid flow and heat transfer in fractured geothermal reservoirs under varying thermodynamic conditions. Fractures with varying conductivities are modeled using the projection-based embedded discrete fracture model (pEDFM) in an explicit manner. The developed ADM method allows the fine-scale system to be mapped to a discrete domain with an adaptive grid resolution via the use of the restriction and prolongation operators. The developed framework is used (a) to investigate the impacts of formulations with different primary variables on the simulation results, and (b) to assess the performance of ADM in a high-enthalpy reservoir by comparing the simulation results against those obtained from fine-scale grids. Results show that the two formulations produce similar results in the case of single-phase flow, which indicates that the molar formulation is a favorable option that can be applied to varying thermodynamic conditions. Moreover, the ADM can provide accurate solutions with only a fraction of fine-scale grids, e.g., for the studied case, the maximum error is by average 1.3 with only 42% of active cells, thereby improving the computational efficiency. This is promising for applying the developed method to field-scale geothermal systems. Full article

Physics-informed neural networks (PINNs) are an emerging technology in the scientific computing domain. Contrary to data-driven methods, PINNs have been shown to be able to approximate and generalize well a wide range of partial differential equations (PDEs) by imbedding the underlying physical laws describing the PDE. PINNs, however, can struggle with the modeling of hyperbolic conservation laws that develop shocks, and a classic example of this is the Buckley–Leverett problem for fluid flow in porous media. In this work, we explore specialized neural network architectures for modeling the Buckley–Leverett shock front. We present extensions of the standard multilayer perceptron (MLP) that are inspired by the attention mechanism. The attention-based model was, compared to the multilayer perceptron model, and the results show that the attention-based architecture is more robust in solving the hyperbolic Buckley–Leverett problem, more data-efficient, and more accurate. Moreover, by utilizing distance functions, we can obtain truly data-free solutions to the Buckley–Leverett problem. In this approach, the initial and boundary conditions (I/BCs) are imposed in a hard manner as opposed to a soft manner, where labeled data are provided on the I/BCs. This allows us to use a substantially smaller NN to approximate the solution to the PDE. Full article

Physics-informed neural network (PINN) models are developed in this work for solving highly anisotropic diffusion equations. Compared to traditional numerical discretization schemes such as the finite volume method and finite element method, PINN models are meshless and, therefore, have the advantage of imposing no constraint on the orientations of the diffusion tensors or the grid orthogonality conditions. To impose solution positivity, we tested PINN models with positivity-preserving activation functions for the last layer and found that the accuracy of the corresponding PINN solutions is quite poor compared to the vanilla PINN model. Therefore, to improve the monotonicity properties of PINN models, we propose a new loss function that incorporates additional terms which penalize negative solutions, in addition to the usual partial differential equation (PDE) residuals and boundary mismatch. Various numerical experiments show that the PINN models can accurately capture the tensorial effect of the diffusion tensor, and the PINN model utilizing the new loss function can reduce the degree of violations of monotonicity and improve the accuracy of solutions compared to the vanilla PINN model, while the computational expenses remain comparable. Moreover, we further developed PINN models that are composed of multiple neural networks to deal with discontinuous diffusion tensors. Pressure and flux continuity conditions on the discontinuity line are used to stitch the multiple networks into a single model by adding another loss term in the loss function. The resulting PINN models were shown to successfully solve the diffusion equation when the principal directions of the diffusion tensor change abruptly across the discontinuity line. The results demonstrate that the PINN models represent an attractive option for solving difficult anisotropic diffusion problems compared to traditional numerical discretization methods. Full article

Numerical models can be used for many purposes in oil and gas engineering, such as production optimization and forecasting, uncertainty analysis, history matching, and risk assessment. However, subsurface problems are complex and non-linear, and making reliable decisions in reservoir management requires substantial computational effort. Proxy models have gained much attention in recent years. They are advanced non-linear interpolation tables that can approximate complex models and alleviate computational effort. Proxy models are constructed by running high-fidelity models to gather the necessary data to create the proxy model. Once constructed, they can be a great choice for different tasks such as uncertainty analysis, optimization, forecasting, etc. The application of proxy modeling in oil and gas has had an increasing trend in recent years, and there is no consensus rule on the correct choice of proxy model. As a result, it is crucial to better understand the advantages and disadvantages of various proxy models. The existing work in the literature does not comprehensively cover all proxy model types, and there is a considerable requirement for fulfilling the existing gaps in summarizing the classification techniques with their applications. We propose a novel categorization method covering all proxy model types. This review paper provides a more comprehensive guideline on comparing and developing a proxy model compared to the existing literature. Furthermore, we point out the advantages of smart proxy models (SPM) compared to traditional proxy models (TPM) and suggest how we may further improve SPM accuracy where the literature is limited. This review paper first introduces proxy models and shows how they are classified in the literature. Then, it explains that the current classifications cannot cover all types of proxy models and proposes a novel categorization based on various development strategies. This new categorization includes four groups multi-fidelity models (MFM), reduced-order models (ROM), TPM, and SPM. MFMs are constructed based on simplifying physics assumptions (e.g., coarser discretization), and ROMs are based on dimensional reduction (i.e., neglecting irrelevant parameters). Developing these two models requires an in-depth knowledge of the problem. In contrast, TPMs and novel SPMs require less effort. In other words, they do not solve the complex underlying mathematical equations of the problem; instead, they decouple the mathematical equations into a numeric dataset and train statistical/AI-driven models on the dataset. Nevertheless, SPMs implement feature engineering techniques (i.e., generating new parameters) for its development and can capture the complexities within the reservoir, such as the constraints and characteristics of the grids. The newly introduced parameters can help find the hidden patterns within the parameters, which eventually increase the accuracy of SPMs compared to the TPMs. This review highlights the superiority of SPM over traditional statistical/AI-based proxy models. Finally, the application of various proxy models in the oil and gas industry, especially in subsurface modeling with a set of real examples, is presented. The introduced guideline in this review aids the researchers in obtaining valuable information on the current state of PM problems in the oil and gas industry. Full article