... Figure 2 Realizations of the generated ensemble on the field level. Data Exploration and Analysis Results and analysis In this section, we highlight the results of the ML models on the test dataset and compare the performance of the different approaches. Experimental Setup...

... decontamination asia government reservoir characterization obm contamination reservoir simulation contamination psat pvt measurement figure 5 composition scenario figure 2 regression realization pvt experiment presented pvt data viscosity delineating figure 4 petroleum technology conference...

... management reservoir simulation reservoir characterization netherlands government injection chemical flooding methods tubing correlation diameter permeability realization subsurface storage artificial intelligence machine learning workflow co2 injection experiment united states government...

... south to north. stationarity reservoir characterization stationarity hypothesis netherlands government consideration geostatistical simulation information europe government upstream oil & gas realization modeling magnitude variance degterev interpolation assumption applicability...

... uncertainty parameters that impact Hydrocarbon volume in place and dynamic uncertainty parameters that impact cumulative hydrocarbon production, including the LGR (extension and permeability). Statistical maps on 100 different geological realizations calculated on mobile hydrocarbon column and permeability...

... PDA results (strong evidence and uncertain data). Screening of initial realizations: comparison of streamlines traced from the reservoir simulation results (of the initial ensemble) against FPCM to discard non-PDA compliant realizations. Then, investigation of the consistency of the initial...

... properties but do not provide quantitative estimates of the subsurface uncertainties. The objective of this study was to carry out a facies dependent geostatistical seismic inversion to generate multi-realization reservoir properties to improve the geological understanding of the two adjacent offshore fields...

... dependency parametric uncertainty realization ensemble seed number lease boundary uncertain parameter geological modeling Upstream Oil & Gas facies workflow rigorous multi-scenario uncertainty analysis society of petroleum engineers equity percentage machine learning compartment...

... be complementary to standard practices of oil saturation mapping and of special value when analyzing the results of multiple realizations and/or development scenarios. where S o is the oil saturation, S or is the residual oil saturation, S oi is the initial oil saturation, and ε represent a very...

... with a reduced subset of model scenarios. Methods based on heuristics and ad-hoc rules exist to select this reduced subset. However, in most of the cases, the optimal number of model realizations must be known upfront. Excessively small number of realizations may result in a subset that does not always capture...

... geology heterogeneity dynamic modeling approach realization fast-track project neptune field calculation interpretation exploration society of petroleum engineers Artificial Intelligence Upstream Oil & Gas ayashsky license area oil field saturation coefficient stoiip distribution...

.... The well controls optimization task now becomes very challenging, because there are thousands of combinations of BHP permutations that are possible, and on top of it all each combination needs to be run on each uncertainty realization to generate a full cumulative density function. This is because...

... max ⁡ ( α E Ω [ N P V ( X ) ] − ( 1 − α ) σ Ω [ N P V ( X ) ] ) , where X is a vector defining the well production/injection parameters, U is the search space, α is a coefficient between [0,1], Ω is a set of realizations, E Ω Ω...

... Abstract Standard approaches to optimization under uncertainty in reservoir simulation require use of multiple realizations, with variable parameters representing operational constraints and actions as well as uncertain scenarios. We will show how appropriate use of local optimization within...

... explore parameter space combined with the least squares single objective function. The process of AHM can adopt parameterization and realization methods to reduce inverse problems. In this study, realizations of various reservoir properties such as porosity, net to gross, relative permeability, horizontal...

...-scaled sector model was built for a focused area of the field with substantial remaining opportunity. Multiple static realizations were used to represent different reservoir connectivity that can be highly influential on the ultimate recovery, especially for iWAG injection. Along with these multi-static...

... by areas. This strategy guaranteed unchanged well data conditioning on all final realizations. geologic modeling reservoir simulation geological modeling Reservoir Characterization Upstream Oil & Gas Artificial Intelligence history matching petrophysical property state vector proportion...

... parameters (nominal optimization). Then, an ensemble of updated model realizations was included within the optimization framework (robust optimization) to represent the residual uncertainty after history matching. In the nominal case we optimized the cumulative oil production over a period of 10 years using...

... range for the depth of horizons accounting for spatial drift. The approach is illustrated with an example for a real clastic reservoir. Reservoir Characterization random field vector realization Artificial Intelligence well data uncertainty quantification order derivative equation partial...

... realization ensemble closed-loop reservoir management seismic survey reservoir model Introduction Over the past decades, new sensing technologies have been boosting the flow of detailed reservoir information from oil and gas fields. Different types of well-based sensors and field-wide data have...