| “Advance Geomechanics, Reservoir Characterization and Imaging Specialist” |
|
|
|
PORE FLUID PREDICTION
|
|
in Complex Reservoir Using Hybrid Rock Physics and Statistical Neural Network
|
|
|
Reservoir characterization plays a crucial role in developing robust dynamic models that facilitate reliable predictions. An effective definition of reservoir rock types should connect geological facies with their petrophysical properties, such as pore fluid.
Rather than focusing solely on porosity and permeability of the rock reservoir, the type of fluid is vital for understanding the hydrocarbon saturation of the reservoir. This knowledge is essential for estimating total reserves and assessing the commercial viability of the accumulation. The saturation of a formation is defined as the proportion of its pore volume that is filled by the considered fluid. Given that direct sampling of the fluid reservoir is neither technically nor commercially efficient, and that laboratory determination of fluid saturation is both costly and time-consuming, the common practice is to use indirect determination through well log measurements.
|
|
| FLUID MAP PREDICTION |
| USING PCA AND ARTIFICIAL INTELLIGENCE METHODS |
 |
|
| WELL TO SEISMIC FLUID SECTION PREDICTION |
| USING PCA AND ARTIFICIAL INTELLIGENCE METHODS |
 |
|
| STATISTICAL SEISMICS ROCK PHYSICS ANALYSIS USING PCA METHODS |
 |
|
