Abstract: A method for history matching a reservoir model based on actual production data from the reservoir over time generates an ensemble of reservoir models using geological data representing petrophysical properties of a subterranean reservoir. Production data corresponding to a particular time instance is acquired from the subterranean reservoir. Normal score transformation is performed on the ensemble and on the acquired production data to transform respective original distributions into normal distributions. The generated ensemble is updated based on the transformed acquired production data using an ensemble Kalman filter (EnKF). The updated generated ensemble and the transformed acquired production data are transformed back to respective original distributions. Future reservoir behavior is predicted based on the updated ensemble.

Abstract: A system is described for estimating well production and injection rates of a subterranean reservoir using machine learning models. The system may include a processor and a non-transitory computer-readable medium comprising instructions that are executable by the processor to cause the processor to perform various operations. The processor may receive a set of static geological data about at least one subterranean reservoir in a subterranean formation. The processor may apply a trained convolutional neural network to the set of static geological data and data on initial states of dynamic reservoir properties to determine dynamic outputs of the subterranean reservoir. The processor may determine well data by extracting the set of static geological data and the dynamic outputs at well trajectories. And, the processor may apply a trained artificial neural network to the well data and subterranean grid information about the subterranean reservoir to generate estimated well production and injection rates.

Abstract: Hybrid 3D geocellular grids are generated to represent a subset of a natural fracture network (“NFN”) directly in the simulation, while the remainder of the NFN is approximated by a multi-continuum formulation. The resulting output is a 3D geocellular grid that possesses a higher level of mesh resolution in those areas surrounding the first fracture subsets, and lower mesh resolution in the areas of the second fracture subset.

Abstract: A system is described for estimating well production and injection rates of a subterranean reservoir using machine learning models. The system may include a processor and a non-transitory computer-readable medium comprising instructions that are executable by the processor to cause the processor to perform various operations. The processor may receive a set of static geological data about at least one subterranean reservoir in a subterranean formation. The processor may apply a trained convolutional neural network to the set of static geological data and data on initial states of dynamic reservoir properties to determine dynamic outputs of the subterranean reservoir. The processor may determine well data by extracting the set of static geological data and the dynamic outputs at well trajectories. And, the processor may apply a trained artificial neural network to the well data and subterranean grid information about the subterranean reservoir to generate estimated well production and injection rates.

Abstract: A method for history matching a reservoir model based on actual production data from the reservoir over time generates an ensemble of reservoir models using geological data representing petrophysical properties of a subterranean reservoir. Production data corresponding to a particular time instance is acquired from the subterranean reservoir. Normal score transformation is performed on the ensemble and on the acquired production data to transform respective original distributions into normal distributions. The generated ensemble is updated based on the transformed acquired production data using an ensemble Kalman filter (EnKF). The updated generated ensemble and the transformed acquired production data are transformed back to respective original distributions. Future reservoir behavior is predicted based on the updated ensemble.

Abstract: Using production data and a production flow record based on the production data, a deep neural network (DNN) is trained to model a proxy flow simulation of a reservoir. The proxy flow simulation of the reservoir is performed, using an ensemble Kalman filter (EnKF), based on the trained DNN. The EnKF assimilates new data through updating a current ensemble to obtain history matching by minimizing a difference between a predicted production output from the proxy flow simulation and measured production data from a field. Using the updated current ensemble, a second proxy flow simulation of the reservoir is performed based on the trained DNN. The assimilating and the performing are repeated while new data is available for assimilating. Predicted behavior of the reservoir is determined based on the proxy flow simulation of the reservoir. An indication of the predicted behavior is provided to facilitate production of fluids from the reservoir.

Abstract: Hybrid 3D geocellular grids are generated to represent a subset of a natural fracture network (“NFN”) directly in the simulation, while the remainder of the NFN is approximated by a multi-continuum formulation.

Abstract: At least some of the disclosed systems and methods obtain a static earth model having a three-dimensional grid with multiple cells. Further, at least some of the disclosed systems and methods determine a plurality of geobodies for the static earth model, each geobody comprising a plurality of connected cells. Further, at least some of the disclosed systems and methods compute one or more tortuosity values for at least one of the plurality of geobodies. Further, at least some of the disclosed systems and methods calibrate the static earth model based on the one or more computed tortuosity values. Further, at least some of the disclosed systems and methods use the calibrated static earth model as input to a flow simulator.

Abstract: The disclosed embodiments include a method, apparatus, and computer program product for generating multiple correlated meshes around complex and discrete fractures for the purpose of reservoir simulation. In an initial two-stage process, a 2.5-dimensional mesher algorithm, may be used in conjunction with an extended anisotropic geometry-adaptive refinement algorithm to produce, from a structured grid Earth Model, a refined reservoir model. Fractures may be modeled as a volumetric mesh that is independent of the refined reservoir model. Thereafter, the two independent, overlapping meshes are combined by forming matrix-matrix, fracture-fracture, and matrix-fracture connections to form a single model to allow rapid simulation of an extremely complex fracture network with sufficiently accurate results.

Abstract: A reservoir simulator system models the effect of proppant damage on reservoir production through calculation of a fracture closure stress versus fracture permeability relationship, which is mathematically transformed into a pore pressure versus fracture permeability relationship. Based upon the pore pressure relationship, the system models reservoir production while taking into account the permeability reduction in the fractures brought about due to proppant damage.

Abstract: Systems and methods for 2D domain decomposition during parallel reservoir simulation to balance the active cells in a reservoir model.

Abstract: The disclosed embodiments include a method, apparatus, and computer program product for generating multiple correlated meshes around complex and discrete fractures for the purpose of reservoir simulation. In an initial two-stage process, a 2.5-dimensional mesher algorithm, may be used in conjunction with an extended anisotropic geometry-adaptive refinement algorithm to produce, from a structured grid Earth Model, a refined reservoir model. Fractures may be modeled as a volumetric mesh that is independent of the refined reservoir model. Thereafter, the two independent, overlapping meshes are combined by forming matrix-matrix, fracture-fracture, and matrix-fracture connections to form a single model to allow rapid simulation of an extremely complex fracture network with sufficiently accurate results.

Abstract: Simulation system and method for a reservoir represented by a model having a plurality of matrix nodes, a plurality of fracture nodes, a fracture zone and a fracture-free zone are described. One embodiment includes computer-implemented steps of, for each of a plurality of matrix nodes in interconnected zones, characterizing the matrix nodes as dual matrix nodes or non-dual matrix nodes. Dual matrix nodes may be treated as a block and eliminated, after which the coefficient matrix and RHS vector for the model are updated. In-fill patterns between and among fracture nodes and non-dual matrix nodes resulting from the elimination are determined. For non-dual matrix nodes, the nodes are merged to a fracture grid, after which the coefficient matrix and RHS vector for the model are updated accordingly. The resultant linear system is linearly solved, and backsolving is performed for any eliminated dual matrix nodes.

Abstract: At least some of the disclosed systems and methods obtain a static earth model having a three-dimensional grid with multiple cells. Further, at least some of the disclosed systems and methods determine a plurality of geobodies for the static earth model, each geobody comprising a plurality of connected cells. Further, at least some of the disclosed systems and methods compute one or more tortuosity values for at least one of the plurality of geobodies. Further, at least some of the disclosed systems and methods calibrate the static earth model based on the one or more computed tortuosity values. Further, at least some of the disclosed systems and methods use the calibrated static earth model as input to a flow simulator.

Abstract: A reservoir simulator system models the effect of proppant damage on reservoir production through calculation of a fracture closure stress versus fracture permeability relationship, which is mathematically transformed into a pore pressure versus fracture permeability relationship. Based upon the pore pressure relationship, the system models reservoir production while taking into account the permeability reduction in the fractures brought about due to proppant damage.

Abstract: Simulation system and method for a reservoir represented by a model having a plurality of matrix nodes, a plurality of fracture nodes, a fracture zone and a fracture-free zone are described. One embodiment includes computer-implemented steps of, for each of a plurality of matrix nodes in interconnected zones, characterizing the matrix nodes as dual matrix nodes or non-dual matrix nodes. Dual matrix nodes may be treated as a block and eliminated, after which the coefficient matrix and RHS vector for the model are updated. In-fill patterns between and among fracture nodes and non-dual matrix nodes resulting from the elimination are determined. For non-dual matrix nodes, the nodes are merged to a fracture grid, after which the coefficient matrix and RHS vector for the model are updated accordingly. The resultant linear system is linearly solved, and backsolving is performed for any eliminated dual matrix nodes.

Abstract: Systems and methods for 2D domain decomposition during parallel reservoir simulation to balance the active cells in a reservoir model.

Abstract: Systems and methods for utilizing finite difference simulation results to compute streamline trajectories, which may be used to analyze the results with other streamline techniques.

Abstract: Systems and methods for utilizing finite difference simulation results to compute streamline trajectories, which may be used to analyze the results with other streamline techniques.