Landmark Graphics Corporation

Halliburton Energy Services, Inc.

Landmark Graphics Corporaton

Terry Wayne Wong

Graham Christopher Fleming

Dominic Camilleri

Yevgeniy Zagayevskiy

Saeedeh Mohebbinia

Srinath Madasu

Amit Kumar

Richard Edward Hinkley

Hui Dong

Hanzi Mao

Harsh Biren Vora

Charles Hai Wang

Courtney Leeann Beck

Harold Grayson Walters

Keshava Prasad Rangarajan

Travis Hope Larsen

Steven Ward

Jianlei Sun

Soumi Chaki

Ron Dusterhoft

ZhiXiang Jiang

Honggeun Jo

Yang Cao

Yuribia Patricia Munoz

Yongchae Cho

A method includes collecting a first set of borehole gravity data at a first time step along a length of a first wellbore and collecting a second set of borehole gravity data at the first time step along a length of a second wellbore. The method also includes interpolating a third set of borehole gravity data at the first time step in an area between the first wellbore and the second wellbore using the first and the second sets of borehole gravity data. Further, the method includes determining a first fluid saturation and a fluid saturation change over time in a reservoir containing the first wellbore and the second wellbore using the first set, the second set, and the third set. Moreover, the method includes controlling wellbore production operations or wellbore injection operations at the first wellbore based on the fluid saturation change.

Gas saturation distribution monitoring in hydrocarbon reservoir

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.

Petroleum reservoir behavior prediction using a proxy flow model

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.

Optimized methodology for automatic history matching of a petroleum reservoir model with Ensemble Kalman Filter (EnKF)

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.

Estimating reservoir production rates using machine learning models for wellbore operation control

A method includes selecting a model for a simulation of hydrocarbon recovery from a reservoir having a plurality of fractures during injection of an injected gas into the plurality of fractures. Selecting the model includes determining a flux ratio of a convection rate to a diffusion rate for the reservoir, determining whether the flux ratio is less than a threshold, and in response to the flux ratio being less than the threshold, selecting the model that includes diffusion. Selecting the model includes performing the simulation of the hydrocarbon recovery from the reservoir based on the model.

Diffusion flux inclusion for a reservoir simulation for hydrocarbon recovery

A system and method for controlling a gas supply to provide gas lift for a production wellbore makes use of Bayesian optimization. A computing device controls a gas supply to inject gas into one or more wellbores. The computing device receives reservoir data associated with a subterranean reservoir to be penetrated by the wellbores and can simulate production using the reservoir data and using a physics-based or machine learning or hybrid physics-based machine learning model for the subterranean reservoir. The production simulation can provide production data. A Bayesian optimization of an objective function of the production data subject to any gas injection constraints can be performed to produce gas lift parameters. The gas lift parameters can be applied to the gas supply to control the injection of gas into the wellbore or wellbores.

Wellbore gas lift optimization

Certain aspects and features relate to a system that projects an optimized foam-fluid-application scenario for to stimulate production from a hydrocarbon well. The optimized scenario can include a recommended chemical make-up for the foam entity as well as application parameters such those related to timing and duration. A hybrid discrete fracture network and multi-porosity (DFN-MP) model for fluid interaction with the formation where the well is located can be produced by a processing device. The hybrid DFN-MP model can be optimized using field simulation data for the formation. The optimized hybrid DFN-MP model can be used by the processing device to produce an optimized foam-fluid-application scenario, which can be communicated to at least one well and can be utilized to stimulate the well for increased production.

Optimized foam application for hydrocarbon well stimulation

Systems, methods, and computer-readable media for forecasting a time to complete a simulation of a reservoir simulation model. A processor can run a simulation of a reservoir simulation model for a first predetermined period of time associated with a first computation step of the simulation. The processor can measure a performance result of the simulation for the first predetermined period of time. The performance result can include an elapsed wall clock time and a timespan simulated. The processor can then forecast a remaining time to complete the simulation of the reservoir simulation model based on the performance result.

Time-to-finish simulation forecaster

In some embodiments, a system, as well as a method and an article, may operate to generate map values for a plurality of parameters corresponding to respective grid blocks of a reservoir, wherein the values have been previously generated based on an initial simulation result from a model of the reservoir; to generate a sector surrogate model that includes a subset of grid blocks of the reservoir based on a criterion for identifying grid blocks that negatively affect simulation of the reservoir; to provide data inputs to execute a simulation of the reservoir using the sector surrogate model; and to generate revised data inputs, based on results of the simulation of the reservoir using the sector surrogate model, to use in a subsequent simulation using the model of the reservoir. Additional apparatus, systems, and methods are disclosed.

Model tuning using boundary flux sector surrogates

A method includes creating a diffusion model for a simulation of hydrocarbon recovery from a reservoir having a plurality of fractures during injection of an injected gas into the plurality of fractures, wherein the reservoir is partitioned into a plurality of grid cells in the diffusion model. Creating the diffusion model for a grid cell of the plurality of grid cells comprises, determining a flux ratio of a convective flux to an estimated diffusive flux for the grid cell, determining whether the flux ratio is less than a threshold, and in response to determining that the flux ratio is less than the threshold, determining a full diffusive flux for the grid cell for inclusion in the diffusion model. The method also includes performing the simulation of the hydrocarbon recovery from the reservoir based on the diffusion model.

Selective diffusion inclusion for a reservoir simulation for hydrocarbon recovery

In some embodiments, a method for locally lumped equation of state fluid characterization can include determining a set of components for the material balance calculations for a plurality of grid blocks of a reservoir. The plurality of grid blocks can experience different recovery methods between them. Lumping schemes can be determined for the plurality of grid blocks. Phase behavior calculations can be performed on the plurality of grid blocks, wherein different lumping schemes can be used across the plurality of grid blocks.

Locally lumped equation of state fluid characterization in reservoir simulation

Systems and methods for determining operating settings of a fluid production system with a gathering network and a plurality of reservoirs, at least some of which include a method that includes lumping common pseudo-components into reservoir pseudo-components associated with each of the reservoirs. Each common pseudo-component is associated with the gathering network and maps to one reservoir pseudo-component of each of the reservoirs. The method further includes performing at least part of a fully-coupled simulation of the gathering network and the reservoirs using the common pseudo-components to obtain one or more operating settings that meet one or more constraints of the production system, and presenting to a user the operating settings.

Systems and methods for solving a multi-reservoir system with heterogeneous fluids coupled to a common gathering network

System and methods of modeling fluids in a simulation of fluid production in a multi-reservoir system with a common surface network are provided. Pressure-volume-temperature (PVT) data is determined for fluids in each of a plurality of reservoirs coupled to the common surface network. A shared equation of state (EOS) characterization representing each of the fluids across the plurality of reservoirs is generated based on the corresponding PVT data. Data representing properties of the fluids in each reservoir is calculated based on the shared EOS characterization of the fluids. When the calculated data is determined not to match the PVT data associated with the fluids in each reservoir, to the shared EOS characterization is adjusted based on a difference between the calculated data and the PVT data.

Shared equation of state characterization of multiple fluids

System and methods of simulating fluid production in a multi-reservoir system with a common surface network are provided. Black oil data is matched with a common equation of state (EOS) model for each of a plurality of reservoirs. The black oil data representing fluids within each reservoir. At least one multi-dimensional black oil table representing a mix of the fluid components to be produced from each of the plurality of reservoirs via the common surface network is generated based on the EOS model that matches the one or more black oil tables for each reservoir. Properties of the fluids in the mix during a simulation of fluid production from the plurality of reservoirs are calculated based on the generated multi-dimensional black oil table for each reservoir.

Growing community of inventors

Houston, TX, United States of America

Terry Wayne Wong