... [ S w − S w i 1 − S w i ] a w +   c o [ 1 − S w − S o r 1 − S o r ] a o Skjaeveland et al. (2000) derived a general capillary pressure correlation ( equation 2 ) for mixed-wet reservoirs based...

...) correlate features and permeability well. For the tested heterogeneous core plugs, the exponential Gaussian Process model performs the best. The R-Squared values of the three sets of training data are 0.88, 0.87 and 0.91 respectively. Afterwards, the selected ML model was tested with additional data...

... dataset used. However, having too many hidden layers does not always render the model more robust. Symbolic Regression This model is one of the oldest models used to generate mathematical correlations between the given parameters. The symbolic regression mechanism relies on mathematical operators...

... studies. The current correlations are restricted by the use of sample from a particular field. As the physical properties and the composition of the crude oil varies the results becomes erroneous after a specific range. This correlation will give results only over a specific range of properties like...

... of permeability ranging from tight to permeable, to compare the generated results between both of the above equipment. The results were graphed and been compared using different point of views, mathematicalwise, petroleum engineeringwise, and geologicalwise. Ultimately, an equation to correlate between...

... to a porosity cutoff, as well as vertical permeability, which is dependent of horizontal permeability from the static realizations. Relative permeabilities were defined as Corey correlations, allowing endpoints and exponents to be varied in the uncertainty workflow. Initial water saturation, residual gas...

... and its porosity partition. Next, it builds the SHF per rock type at special core analysis (SCAL) level using a novel approach based on a symbolic regressor logic. This automatically defines the best correlation of the extracted fitting coefficients to core porosity and permeability while honoring...

... recovery wax remediation eos asphaltene remediation production chemistry hydrate remediation flow assurance paraffin remediation abu dhabi international petroleum exhibition conference asphaltene precipitation experiment reproduce correlation asphaltene envelope Although in some...

... reservoir characterization exhibition huban eage conference complex reservoir inversion acquisition interpretation correlation late jurassic carbonate reservoir non-repeated obc geometry seismic acquisition brechet simulation seismic monitoring lafram repeatability noise phase-1 sequence...

... this novel approach. Real-time density/neutron does not have good correlation with modelled density /neutron due to gas effect. Such poor correlation can be attributed to proximity to a Gas Oil Contact (GOC) and dynamic invasion, complicating the real-time geo-steering. However, real-time total porosity from...

... Although good correlation between measured and modelled logs was achieved using the adjusted mineral properties of Dolomite and Anhydrite, test 7 refined the results at the calibration wells which gave highest CC and lowest NRMS. Test 7: estimated aspect ratio log per well per formation...

... used to identify in real-time the lithology and to interpret the formation fluids; well-to-well log correlation and look ahead, models used to find analogies between intervals of the well being drilled and the reference well, allowing to estimate the distance and time of arrival to a given geological...

... and storage (CCS) within the unified framework of classical compositional reservoir simulation by employing the standard volume-translated Peng-Robinson (PR-VT) Equation of State (EOS) and Lohrenz-Bray-Clark (LBC) viscosity correlation. We spend tremendous effort on the collection of high-quality data and our...

.... Finally, forced imbibition was performed on all cores using coreflood to generate CDC using three different surfactants with varying IFT values. The results showed that all rock samples achieved initial water saturation (S wi ) in the range of 18-32% with no correlation between S wi and rock...

.... Reservoir Characterization Artificial Intelligence Fluid Dynamics water saturation flow in porous media Leverett porosity capillary pressure curve interfacial tension Engineer saturation-height function permeability Upstream Oil & Gas correlation transition zone saturation equation...

... and Soave-Redlich-Kwong EOS. Third, statistical analysis is performed to determine the level of confidence of the different methods. Fourth, a correlation to determine the optimal number of pseudo-components is defined. These steps include: Characterization of fluid and heavy components Tuning...

... and Production logging information. This approach has allowed to obtain a Karst/No Karst Supervised dataset for about 60 wells. In the second phase different seismic and geological attributes have been considered in order to investigate possible correlations with karst features. In fact there are some...

... Abstract This study examines which is the margin of usability for Artificial Intelligence (AI) algorithms related to the rock properties distribution in static modeling. This novel method shows a forward modeling approach using neural networks and genetic algorithms to optimize correlation...

... creates a set of new problems. First of all, there is no exact procedure for such splitting. Thus, it is unclear how to select regions in advance and run just one optimization cycle. Furthermore, the independent variation of such variables distortsthe correlation between porosity and permeability...

... the discrepancy between data input and model output while continuously honoring the data, maintaining realistic correlations (e.g. between static permeability and water saturation) and respecting inherent uncertainty. Using a data-rich Middle East carbonate reservoir, the pre- and post-diagnostic comparison...