Layer | Fill | Outline |
---|
Map layers
Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|
Fill | Stroke |
---|---|
Collaborating Authors
Results
Abstract Routine well-wise injection/production data contain significant information which can be used for closed-loop reservoir management and rapid field decisions. Traditional physics-based numerical reservoir simulation can be computationally prohibitive for short-term decision cycles, and also requires detailed geologic model. Reduced physics models provide an efficient simulator free workflow, but often have a limited range of applicability. Pure machine learning models lack physical interpretability and can have limited predictive power. We propose a hybrid machine learning and physics-based approach for rapid production forecasting and reservoir connectivity characterization using routine injection/production and pressure data. Our framework takes routine measurements such as injection rate and pressure data as input and multiphase production rates as output. We combine reduced physics models into a neural network architecture by utilizing two different approaches. In the first approach, the reduced physics model is used for pre-processing to obtain approximate solutions that feed it into a neural network as input. This physics-based input feature can reduce the model complexity and provide significant improvement in prediction performance. The second approach augments the residual terms in the neural network loss function with physics-based regularization that relies on the governing partial differential equations (PDE). Reduced physics models are used for the governing PDE to enable efficient neural network training. The regularization allows the model to avoid overfitting and provides better predictive performance. Our proposed hybrid models are first validated using a 2D benchmark reservoir simulation case and then applied to a field-scale reservoir case to show the robustness and efficiency of the method. The hybrid models are shown to provide superior prediction performance than pure machine learning models and reduced physics models in terms of multiphase production rates. Specifically, in the second method, the trained hybrid neural network model satisfies the reduced physics model, making it physically interpretable, and provides inter-well connectivity in terms of well flux allocation. The flux allocation estimated from the hybrid model was compared with streamline-based flux allocation, and excellent agreement was obtained. By combining the reduced physics model with the efficacy of deep learning, model calibration can be done very efficiently without constructing a geologic model. The proposed hybrid models with physics-based regularization and preprocessing provide novel approaches to augment data-driven models with underlying physics to build interpretable models for understanding reservoir connectivity between wells and robust future production forecasting.
- Energy > Oil & Gas > Upstream (1.00)
- Government > Regional Government > North America Government > United States Government (0.68)
Streamline Tracing and Applications in Dual Porosity Dual Permeability Models
Onishi, Tsubasa (Texas A&M University) | Chen, Hongquan (Texas A&M University) | Xie, Jiang (Chevron Technical Center) | Tanaka, Shusei (Chevron Technical Center) | Kam, Dongjae (Chevron Technical Center) | Wang, Zhiming (Chevron Technical Center) | Wen, Xian-Huan (Chevron Technical Center) | Datta-Gupta, Akhil (Texas A&M University)
Abstract Streamline-based methods have proven to be effective for various subsurface flow and transport modeling problems. However, the applications are limited in dual-porosity and dual-permeability (DPDK) system due to the difficulty in describing interactions between matrix and fracture during streamline tracing. In this work, we present a robust streamline tracing algorithm for DPDK models and apply the new algorithm to rate allocation optimization in a waterflood reservoir. In the proposed method, streamlines are traced in both fracture and matrix domains. The inter-fluxes between fracture and matrix are described by switching streamlines from one domain to another using a probability computed based on the inter-fluxes. The approach is fundamentally similar to the existing streamline tracing technique and can be utilized in streamline-assisted applications, such as flow diagnostics, history matching, and production optimization. The proposed method is benchmarked with a finite-volume based approach where grid-based time-of-flight was obtained by solving the stationary transport equation. We first validated our method using simple examples. Visual time-of-flight comparisons as well as tracer concentration and allocation factors at wells show good agreement. Next, we applied the proposed method to field scale models to demonstrate the robustness. The results show that our method offers reduced numerical artifacts and better represents reservoir heterogeneity and well connectivity with sub-grid resolutions. The proposed method is then used for rate allocation optimization in DPDK models. A streamline-based gradient free algorithm is used to optimize net present value by adjusting both injection and production well rates under operational constraints. The results show that the optimized schedule offers significant improvement in recovery factor, net present value, and sweep efficiency compared to the base scenario using equal rate injection and production. The optimization algorithm is computationally efficient as it requires only a few forward reservoir simulations.
- Research Report > New Finding (0.87)
- Research Report > Experimental Study (0.54)
- Asia > Kazakhstan > West Kazakhstan > Uralsk Region > Precaspian Basin > Karachaganak Field (0.99)
- Asia > Kazakhstan > West Kazakhstan > Precaspian Basin (0.99)
- Asia > Kazakhstan > Mangystau Oblast > Precaspian Basin > Tengiz Field > Tengiz Formation (0.99)
- (4 more...)
Modeling Hydraulically Fractured Shale Wells Using the Fast Marching Method with Local Grid Refinements LGRs and Embedded Discrete Fracture Model EDFM
Xue, Xu (Texas A&M University) | Yang, Changdong (Texas A&M University) | Onishi, Tsubasa (Texas A&M University) | King, Michael J. (Texas A&M University) | Datta-Gupta, Akhil (Texas A&M University)
Abstract Recently the Fast Marching Method (FMM) based flow simulation has shown great promise for rapid modeling of unconventional oil and gas reservoirs. Currently, the application of FMM-based simulation has been limited to the use of tartan grid to model the hydraulic fractures (HFs). The use of tartan grids adversely impacts the computational efficiency, particularly for field-scale applications with hundreds of HFs. This paper is aimed at extending the FMM-based simulation to incorporate local grid refinements (LGRs) and embedded discrete fracture model (EDFM) to simulate HFs with natural fractures and validating the accuracy and efficiency of the methodologies. The FMM-based simulation is extended to LGRs and EDFM. This requires novel gridding through introduction of triangles (in 2D) and tetrahedrons (in 2.5D) to link the local and global domain and solution of the Eikonal equation in unstructured grids to compute the ‘diffusive time of flight'. The FMM-based flow simulation reduces 3D simulation to an equivalent 1D simulation using the ‘diffusive time of flight (DTOF)’ as a spatial coordinate. The 1D simulation can be carried out using standard finite-difference method leading to orders of magnitude savings in computation time compared to full 3D simulation for high-resolution models. We first validate the accuracy and computational efficiency of the FMM-based simulation with LGRs by comparing with tartan grids. The results show good agreements and the FMM-based simulation with LGRs shows significant improvement in computational efficiency. Then, we apply the FMM based simulation with LGRs to a multi-stage hydraulically fractured horizontal well with multiphase flow case to demonstrate the practical feasibility of our proposed approach. After that, we investigate various discretization schemes for the transition between local and global domain in the FMM-based flow simulation. The results are used to identify optimal gridding schemes to maintain accuracy while improving computational efficiency. Finally, we demonstrate the workflow of the FMM-based simulation with EDFM, including grid generation, comparison with FMM with unstructured grid and validation of the results. The FMM with EDFM can simulate arbitrary fracture patterns without simplification and shows good accuracy and efficiency. This is the first study to apply the FMM-based flow simulation with LGRs and EDFM. The three main contributions of the proposed methodology are: (i) unique mesh generation schemes to link fracture and matrix flow domains (ii) diffusive time of flight calculations in locally refined grids (iii) sensitivity studies to identify optimal discretization schemes for the FMM-based simulation.
- Asia (1.00)
- North America > United States > Texas (0.94)
- Geology > Geological Subdiscipline > Geomechanics (0.68)
- Geology > Rock Type > Sedimentary Rock > Clastic Rock > Mudrock > Shale (0.50)
- Geophysics > Seismic Surveying (0.68)
- Geophysics > Borehole Geophysics (0.68)
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (21 more...)
Abstract Chemical enhanced oil recovery (EOR) methods have received increased attention in recent years since they have the ability to recover the capillary trapped oil. Successful chemical flooding application requires accurate numerical models and reliable forecast across multiple scales: core scale, pilot scale, and field scale. History matching and optimization are two key steps to achieve this goal. For history matching chemical floods, we propose a general workflow for multi-stage model calibration using an Evolutionary Algorithm. A comprehensive chemical flooding simulator is used to model important physical mechanisms including phase behavior, cation exchange, chemical and polymer adsorption and capillary desaturation. First, we identify dominant reservoir and process parameters based on a sensitivity analysis. The history matching is then carried out in a stage-wise manner whereby the most dominant parameters are calibrated first and additional parameters are incorporated sequentially until a satisfactory data misfit is achieved. Next, a diverse subset of history matched models is selected for optimization using a Pareto-based multi-objective optimization approach. Based on the concept of dominance, Pareto optimal solutions are generated representing the trade-off between increasing oil recovery while improving the efficiency of chemical usage. These solutions are searched using a Non-dominated Sorting Genetic Algorithm (NSGA-II). Finally we implement a History Matching Quality Index (HMQI) with Moving Linear Regression Analysis to evaluate simulation results from history matching process. The HMQI provides normalized values for all objective functions having different magnitude and leads to a more consistent and robust approach to evaluate the updated models through model calibration.
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (23 more...)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Optimization (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Evolutionary Systems (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Regression (0.55)
Abstract Hydraulic fracturing treatment in naturally fractured unconventional reservoirs generally induce complex fracture geometries. Thus an unstructured grid, instead of a Cartesian or corner point grid, is preferred to accurately model the geometry of the fractures and the performance of such reservoirs. The drawback of conventional simulation on unstructured grids is the potentially heavy computational cost. A novel approach has recently been introduced to provide rapid simulation of unconventional reservoirs, which first captures the drainage volume during the transient propagation process using the Fast Marching Method (FMM) and then rapidly solves fluid flow equation in an equivalent 1D domain. However, this application is currently limited to calculating the reservoir response with Cartesian or corner-point grids. In this study, the FMM based simulation method is extended to unstructured grid. A new mesh generation approach is first presented to discretize the complex fracture network, accounting for both hydraulic fractures and natural fractures. Voronoi cells (or perpendicular bisector, i.e. PEBI grids) are constructed with high resolution near the fractures and with larger cells far from fractures. A force-equilibrium algorithm is adopted here to optimize the mesh quality and reduce highly skewed cells. FMM algorithm is computed on the basis of subdivided triangles, which can provide the diffusive time of flight (DToF) at both Voronoi cell vertices and cell centers. Thus, a more accurate calculation of drainage volume in unconventional reservoir with complex fracture networks can be obtained. Finally, fluid flow is calculated in transformed 1D domain, where DToF acts as the 1D spatial coordinate. Unstructured grids with good mesh quality are constructed to accurately capture the complex fracture network system. The convergence characteristic of FMM on unstructured grids is investigated. Reservoir simulation is efficiently computed based on the drainage volume information from the unstructured grid system using FMM, and the simulation results are validated with finite-difference based and finite-volume based numerical results. There are three key parts of this proposed approach, which are: (i) good mesh generation technique to capture complex fracture networks, (ii) FMM computation on unstructured grids to provide the drainage volume, and (iii) fluid flow calculation in transformed 1D domain. We extend the reservoir simulation using FMM in unconventional reservoirs from Cartesian and corner point grid systems to unstructured grids. The proposed approach shows orders of magnitude reduction in simulation time for modeling unstructured grids, bringing typical simulation times of hours or days down to minutes, which is quite attractive for high-resolution models. Through the numerical examples, the proposed method is demonstrated to be an accurate and efficient approach to simulate naturally fractured unconventional reservoirs with unstructured grids.
- Information Technology > Modeling & Simulation (0.75)
- Information Technology > Artificial Intelligence (0.48)
- Information Technology > Communications > Networks (0.34)