Abstract: There is provided a method for modeling a hydrocarbon reservoir that includes generating a reservoir model comprising a plurality of sub regions. At least one of the sub regions is simulated using a training simulation to obtain a set of training parameters comprising state variables and boundary conditions of the at least one sub region. A machine learning algorithm is used to approximate, based on the set of training parameters, an inverse operator of a matrix equation that provides a solution to fluid flow through a porous media. The hydrocarbon reservoir can be simulated using the inverse operator approximated for the at least one sub region. The method also includes generating a data representation of a physical hydrocarbon reservoir can be generated in a non-transitory, computer-readable, medium based, at least in part, on the results of the simulation.

Abstract: A method of enhancing a geologic model of a subsurface region is provided. A bed topography of the subsurface region is obtained. The bed topography is defined by a plurality of cells with an elevation associated with each cell center. The bed topography is represented as a cell-centered piecewise constant representation based on the elevations associated with the cells. The bed topography is reconstructed to produce a spatially continuous surface. Flux and gravitational force-related source terms are calculated based on the reconstructed bed topography. Fluxes are calculated between at least two of the cells. Fluid flow, deposition of sediments onto the bed, and/or erosion of sediments from the bed are predicted using the fluxes and gravitational force-related source terms. The predictions are inputted into the geologic model to predict characteristics of the subsurface region, and the predicted characteristics are outputted.

Abstract: There is provided a method for modeling a hydrocarbon reservoir that includes generating a reservoir model that has a plurality of sub regions. A solution surrogate is obtained for a sub region by searching a database of existing solution surrogates to obtain an approximate solution surrogate based on a comparison of physical, geometrical, or numerical parameters of the sub region with physical, geometrical, or numerical parameters associated with the existing surrogate solutions in the database. If an approximate solution surrogate does not exist in the database, the sub region is simulated using a training simulation to obtain a set of training parameters comprising state variables and boundary conditions of the sub region. A machine learning algorithm is used to obtain a new solution surrogate based on the set of training parameters. The hydrocarbon reservoir can be simulated using the solution surrogate obtained for the at least one sub region.

Abstract: A method for modeling a dynamic system (e.g., geological system) comprises: constructing an input parameter space for a model of the geological system, the input parameter space including more than three dimensions, and the model associated with response data, representing the input parameter space visually with three or fewer dimensions, reducing the input parameter space by conditioning the parameter space using at least a subset of the response data, and updating the representation of the input parameter space to visually represent the reduction of the parameter space.

Abstract: There is provided a method for modeling a hydrocarbon reservoir that includes generating a reservoir model that has a plurality of coarse grid cells. A plurality of fine grid models is generated, wherein each fine grid model corresponds to one of the plurality of coarse grid cells that surround a flux interface. The method also includes simulating the plurality of fine grid models using a training simulation to obtain a set of training parameters, including a potential at each coarse grid cell surrounding the flux interface and a flux across the flux interface. A machine learning algorithm is used to generate a constitutive relationship that provides a solution to fluid flow through the flux interface. The method also includes simulating the hydrocarbon reservoir using the constitutive relationship and generating a data representation of a physical hydrocarbon reservoir in a non-transitory, computer-readable medium based on the results of the simulation.

Abstract: A method of enhancing a geologic model of a subsurface region is provided. A bed topography of the subsurface region is obtained. The bed topography is defined by a plurality of cells with an elevation associated with each cell center. The bed topography is represented as a cell-centered piecewise constant representation based on the elevations associated with the cells. The bed topography is reconstructed to produce a spatially continuous surface. Flux and gravitation al force-related source terms are calculated based on the reconstructed bed topography. Fluxes are calculated between at least two of the cells. Fluid flow, deposition of sediments onto the bed, and/or erosion of sediments from the bed are predicted using the fluxes and gravitational force-related source terms. The predictions are inputted into the geologic model to predict characteristics of the subsurface region, and the predicted characteristics are outputted.

Abstract: A method of enhancing a geologic model of a subsurface region is provided. A bed topography of the subsurface region is obtained. The bed topography is defined by a plurality of cells with an elevation associated with each cell center. The bed topography is represented as a cell-centered piecewise constant representation based on the elevations associated with the cells. The bed topography is reconstructed to produce a spatially continuous surface. Flux and gravitational force-related source terms are calculated based on the reconstructed bed topography. Fluxes are calculated between at least two of the cells. Fluid flow, deposition of sediments onto the bed, and/or erosion of sediments from the bed are predicted using the fluxes and gravitational force-related source terms. The predictions are inputted into the geologic model to predict characteristics of the subsurface region, and the predicted characteristics are outputted.

Abstract: A method is presented for modeling reservoir properties. The method includes constructing a coarse computational mesh for the reservoir. The coarse computational mesh comprises a plurality of cells. The method further includes determining a plurality of flows for each of the plurality of cells based on Dirichlet boundary conditions. Additionally, the method includes determining a solution to a coarse pressure equation for the reservoir based on the plurality of flows.

Abstract: A method of forming a geologic model of a subsurface region is disclosed. Data related to the subsurface region is obtained. A framework is constructed to represent the subsurface region. A template is selected from a plurality of templates. The selected template provides at least one property that is characteristic of the subsurface region. The selected template is inserted into the framework, to form the geologic model. The geologic model is then outputted.

Abstract: A method of generating a model of a turbidity current in a fluid is disclosed. A first flow layer in the turbidity current is defined. The method successively defines at least one more flow layer in the turbidity current. Each successive flow layer includes the previously defined flow layer. A set of depth-averaged flow variables for each flow layer is defined. A model is developed that describes the turbidity current. The model uses fluid flow equations and the set of depth-averaged flow variables for each flow layer to predict fluid flow in each flow layer. The model is then output.

Abstract: A method of forming a geologic model of a subsurface region is disclosed. Data related to the subsurface region is obtained. A framework is constructed to represent the subsurface region. A template is selected from a plurality of templates. The selected template provides at least one property that is characteristic of the subsurface region. The selected template is inserted into the framework, to form the geologic model. The geologic model is then outputted.

Abstract: The present application describes a method and system associated with the production of hydrocarbons. In the method, fluid travel time models are constructed from a reservoir model. Then, reservoir connectivity measures are calculated from the fluid travel time models and analyzed to determine a location for at least one well. Based on the analysis, one or more wells may be drilled and hydrocarbons produced.

Abstract: Techniques are disclosed for performing time-lapse monitor surveys with sparsely sampled monitor data sets. An accurate 3D representation (e.g., image) of a target area (e.g., a hydrocarbon bearing subsurface reservoir) is constructed (12) using the sparsely sampled monitor data set (11). The sparsely sampled monitor data set may be so limited that it alone is insufficient to generate an accurate 3D representation of the target area, but accuracy is enabled through use of certain external information (14). The external information may be one or more alternative predicted models (25) that are representative of different predictions regarding how the target area may change over a lapse of time. The alternative models may, for example, reflect differences in permeability of at least a portion of the target area. The sparsely sampled monitor data set may then be processed to determine (23) which of the alternative models is representative of the target area.

Abstract: Systems and methods for providing a reservoir simulation are based on data from an unstructured grid using a structured grid reservoir simulator. Exemplary methods comprise obtaining an unstructured grid reservoir model comprising a reservoir model discretized on an unstructured grid. A virtual structured grid is defined for the unstructured grid reservoir model. The unstructured grid is aligned with the virtual structured grid by adding cells to the unstructured grid to make the unstructured grid and virtual structured grid have the same number of cells. The virtual structured grid may be represented in the unstructured grid. Structured grid reservoir simulator input data comprising reservoir model data assigned to the virtual structured grid is prepared based on reservoir model data in the unstructured grid model. A structured grid reservoir simulation is performed using the structured grid reservoir simulator input data to produce a reservoir simulation.

Abstract: A method is presented for modeling reservoir properties. The method includes constructing a coarse computational mesh for the reservoir. The coarse computational mesh comprises a plurality of cells. The method further includes determining a plurality of flows for each of the plurality of cells based on Dirichlet boundary conditions. Additionally, the method includes determining a solution to a coarse pressure equation for the reservoir based on the plurality of flows.

Abstract: There is provided a method for modeling a hydrocarbon reservoir that includes generating a reservoir model that has a plurality of coarse grid cells. A plurality of fine grid models is generated, wherein each fine grid model corresponds to one of the plurality of coarse grid cells that surround a flux interface. The method also includes simulating the plurality of fine grid models using a training simulation to obtain a set of training parameters, including a potential at each coarse grid cell surrounding the flux interface and a flux across the flux interface. A machine learning algorithm is used to generate a constitutive relationship that provides a solution to fluid flow through the flux interface. The method also includes simulating the hydrocarbon reservoir using the constitutive relationship and generating a data representation of a physical hydrocarbon reservoir in a non-transitory, computer-readable medium based on the results of the simulation.

Abstract: There is provided a method for modeling a hydrocarbon reservoir that includes generating a reservoir model that has a plurality of sub regions. A solution surrogate is obtained for a sub region by searching a database of existing solution surrogates to obtain an approximate solution surrogate based on a comparison of physical, geometrical, or numerical parameters of the sub region with physical, geometrical, or numerical parameters associated with the existing surrogate solutions in the database. If an approximate solution surrogate does not exist in the database, the sub region is simulated using a training simulation to obtain a set of training parameters comprising state variables and boundary conditions of the sub region. A machine learning algorithm is used to obtain a new solution surrogate based on the set of training parameters. The hydrocarbon reservoir can be simulated using the solution surrogate obtained for the at least one sub region.

Abstract: There is provided a method for modeling a hydrocarbon reservoir that includes generating a reservoir model comprising a plurality of sub regions. At least one of the sub regions is simulated using a training simulation to obtain a set of training parameters comprising state variables and boundary conditions of the at least one sub region. A machine learning algorithm is used to approximate, based on the set of training parameters, an inverse operator of a matrix equation that provides a solution to fluid flow through a porous media. The hydrocarbon reservoir can be simulated using the inverse operator approximated for the at least one sub region. The method also includes generating a data representation of a physical hydrocarbon reservoir can be generated in a non-transitory, computer-readable, medium based, at least in part, on the results of the simulation.

Abstract: There is provided a method for modeling a hydrocarbon reservoir that includes generating a reservoir model comprising a plurality of coarse grid cells. The method includes generating a fine grid model corresponding to one of the coarse grid cells and simulating the fine grid model using a training simulation to generate a set of training parameters comprising boundary conditions of the coarse grid cell. A machine learning algorithm may be used to generate, based on the set of training parameters, a coarse scale approximation of a phase permeability of the coarse grid cell. The hydrocarbon reservoir can be simulated using the coarse scale approximation of the effective phase permeability generated for the coarse grid cell. The method also includes generating a data representation of a physical hydrocarbon reservoir in a non-transitory, computer-readable, medium based at least in part on the results of the simulation.

Abstract: The invention is a method of modeling a hydrocarbon reservoir. A parameter value in a set of equations is adjusted so that the output of the equations accurately matches observed sediment erosion and deposition behavior for sediment sizes throughout a range of about 10 microns to about 10 centimeters. An initial condition of a sediment bed in the hydrocarbon reservoir is defined. The equations are applied to the initial condition, wherein outputs of the equations express how a fluid flow affects erosion and deposition of sediments at the initial condition. The initial condition is adjusted based on the equation outputs to create a subsequent sediment bed condition. The equations are re-applied to the subsequent sediment bed condition a pre-determined number of times. The subsequent sediment bed condition is re-adjusted after each re-application of the equations. The model of the hydrocarbon reservoir is created and outputted.