The representation learning problem in the oil & gas industry aims to construct a model that provides based on logging data for well interval. Previous attempts are mainly supervised and focus similarity task, which estimates closeness between intervals. We desire build informative representations without using (labelled) data. One of possible approaches is self-supervised (SSL). In contrast pa...

The conventional approach in reservoir characterization uses an extrapolation of petrophysical properties calculated from well logs determining the entire field volume. This technique fails to acknowledge/ factor heterogeneity a reservoir, and consequently leads errors capacity quantification. research work employs deterministic seismic inversion each sand. First, sand was identified intervals ...

Reservoir characterization This paper gives an overview of the activities in geostatistics for the Petroleum industry in the domain of reservoir characterization. This description has been simplified in order to emphasize the original techniques involved. The main steps of a study consist in successively building: • the reservoir architecture where the geometry of the units is established, • th...

Two reservoirs domiciled in a well have been analysed this study order to obtain the quantitative reservoir properties. These properties are essential not only for development and optimization but also accurate decision-making prior exploitation production. A suite of composite logs comprising caliper log, gamma-ray (GR) density resistivity sonic transit time obtained from field onshore Niger D...

Porosity is important because it reflects the presence of oil reserves. Hence, number underground reserves and a direct influence on essential petrophysical parameters, such as permeability saturation, are related to connected pores. Also, selection perforation interval recommended drilling additional infill wells. For estimation two distinct methods used obtain results: first method based conv...

[1] Direct estimation of groundwater solute concentrations from geophysical tomograms has been only moderately successful because (1) reconstructed tomograms are often highly uncertain and subject to inversion artifacts, (2) the range of subsurface conditions represented in data sets is incomplete because of the paucity of colocated well or core data and aquifer heterogeneity, and (3) geophysic...