... intelligence production control prediction neural network co 2 workflow dataset upstream oil & gas north america government production monitoring akhil datta-gupta saturation field-scale application validation dataset realization plume migration application optimization multiplier 0...

... functions are used to train the model: a supervised-learning-based reconstruction loss, a style loss ( Liu & Durlofsky, 2021 ), and a hard data loss. These three loss functions allow creating realizations that conserve higher order of statistic while they respect the hard data and generalizing...

... algorithm conditional realization optimization algorithm a-dgn optimizer oliver uncertainty quantification matrix iteration realization method sensitivity matrix The remainder of this paper is organized as follows: In the next (second) section, we discuss the limitations of the S-DGN...

... field realization locating infill target petroleum engineer Introduction In the reservoir engineering domain, one of the main challenges is the dynamic data conditioning process to match the simulated production profiles to the measured dynamic data. This process is mathematically defined...

.... fluid dynamics optimization problem optimization machine learning upstream oil & gas flow in porous media enhanced recovery realization waterflooding modeling & simulation placement optimization denote workflow accelerate depletion planning optimization reservoir characterization...

.... Fig C-1. Influence of realizations of permeability fields on H 2 upward migration behaviors. (a) and (b) are based on different realizations but with the same set of heterogeneity indicators ( V Dp =0.65, λ Dx = 0.02). The initially emplaced H 2 volume is 0.17 PV, and the saturation fields...

... study. We consider the history matching stage of the study and utilize the multi-well fast modeling approach to determine the rank quality of the 100+ static realizations provided in the benchmark dataset against historical data. The multi-well calculation uses superposition to obtain a direct...

... Before describing the details, we will present definitions of some terms which are repeatedly used within this paper. Ensemble : A collection of unique geologic realizations (models). Initial Ensemble : A collection of cases that incorporates all the uncertainty in input data that has...

... parameters that affect the objective of interests (i.e., CO 2 leakage rates). For the identified uncertainty parameters, various realizations are then generated based on Latin Hypercube Sampling (LHS). High-fidelity simulations based on a two-phase black-oil solver within MRST are performed to generate...

... fluid dynamics reactivation contract decision-making process scenario water injector compartment development scenario producer realization incremental recovery factor workflow conversion Introduction Producing oil at a lower cost to stay competitive in the market is one...

... heterogeneity on CO 2 flow, we built a series of flow simulation models that captured these geostatistical characteristics of permeability, while considering k z realizations, flow regimes (e.g., buoyant flow), CO 2 injection strategies, and reservoir heterogeneity. CO 2 flow simulations showed...

... reservoir simulation fluid dynamics co 2 realization multi-objective optimization effective plastic strain geomechanical property equation injection geomechanical risk Introduction Geological carbon sequestration (GCS) is proposed as a mitigation strategy to reduce anthropogenic CO 2...

... realizations. As a result, suggestions for a more robust parameterization of the ensemble were made to improve data coverage. The existing history matching workflow efficiently integrated with the quantitative 4D seismic history matching workflow allowing for the conditioning of the reservoir models...

... from selected cluster spacing realizations are run with high and low permeability scenarios to show the importance of correct matrix permeability inputs in determining the three-dimensional depletion profile and ultimate production. By varying the cluster spacing we show the hydraulic fracture...

... discontinuities at NNCs. The flux reconstruction allows us to trace streamlines and compute the time of flight (TOF) in DPDK models. The fracture identification workflow relies on the streamline-based analytic sensitivity computation and rapid model calibration using dynamic data. Multiple realizations...

... oil & gas risk management field development optimization and planning standard development downside risk development case decision maker algorithm production rate realization oil price artificial intelligence reservoir simulation investment olympus case reservoir uncertainty drill...

... is to be performed at the full field-level and over multiple geologic realizations. A machine-learning (ML) based approach which is quick and scalable for rate optimization over multiple geologic realizations is proposed instead. The training data for the model is generated by running the forward simulator...

... of fractal dimension for characterizing the fault network and its impact on the subseismic models and fluid displacement, consequently on production. Artificial Intelligence brazilian pre-salt reservoir length analysis Reservoir Characterization reservoir simulation sub-seismic fault realization...

... Bayesian Inference reservoir-pressure data dynamic model Artificial Intelligence Upstream Oil & Gas model parameter application preconditioner permeability field vector grid equation algorithm model maturation realization adjoint method matrix ensemble model maturation adjoint...

... simulation runs. In addition, the training of CNN is implemented using only geologic realizations without requiring additional reservoir simulation. The performance of the workflow is evaluated using tomographic inversion and model calibration in fluvial reservoirs. geologic modeling artificial...