Abstract:
The study's primary goal is to identify the thin sands packages of B and C Intervals of the Lower Goru Formation of the Gambat Latif block, by using machine learning along with reservoir characterization by performing seismic interpretation, seismic inversion,
petrophysics and seismic attributes. The Gambat-Latif region is situated within the Lower Indus Basin of Pakistan, and its geological setting is characterized by extensional tectonic processes. Following the completion of seismic interpretation, seismic inversion, and petrophysical analysis, the findings indicate that the C Interval of the Lower Goru Formation within the Gambat Latif block exhibits a more substantial hydrocarbon potential when contrasted with the B-Interval. Seismic attributes were employed to detect the presence of slender sand units, and it was noted that the Spectral Decomposition attribute produced the most reliable results. This attribute effectively delineated specific zones within both the B and C sands, and the thinner sand beds within the Lower Goru B and C intervals The thin sand beds within the Lower Goru B and C intervals in the Tajjal 02 well became more prominently evident as the frequency spectrum of the spectral decomposition attribute was increased Moreover, machine learning methodologies were utilized to calculate and validate the shear sonic values, both computed from the Castagna equation and those computed using machine learning techniques. It was noted that the Machine Learning-based computation of Vs demonstrated greater reliability and yielded better results when contrasted with the Castagna equation method. Machine Learning was also employed for facies analysis, resulting in the categorization of facies into three distinct lithological packages: sand, shale,
and tight sand. The last encompassed the utilization of machine learning techniques for geomechanical analysis, during which several geomechanical parameters, such as overburden pressure, pore pressure, and fracture gradient, were computed.
