Reservoir Characterization of Sawan Gas Field using Seismic Inversion and Machine Learning Algorithms, Central Indus Basin, Pakistan

Abstract

The study's primary goal is to identify the thin sands packages of B and C Intervals of Lower Goru Formation of Sawan Gas Field, by using machine learning along with reservoir characterization by performing seismic interpretation, seismic inversion, petrophysics, Rock physics modeling and using machine learning algorithms. The Sawan Gas Field is situated within the Central 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 Sawan Gas Field exhibits a more substantial hydrocarbon potential when contrasted with the B-Interval. Rock physics modeling has been used for the prediction of P and S wave variations and how Poisson’s ratio occurs. Rock physics depicted the missing log prediction like S-wave specifically and fluid substitution also occurred with different conditions to confirm reservoir availability. Model-Based Inversion (MBI) has been used to predict and confirm more better results came from seismic interpretation. The wavelet was extracted from the control line and the correlation occurred. LFM (Low Frequency Models) have been generated as well. Afterwards, Quality control of data occurred by inverted techniques. Lastly to confirm results with the seismic inversion technique, Machine learning (PNN) based on the Bayesian classifier method which gives reliable prediction of petrophysical properties, so it is used predict the Volume of clay prediction, Porosity prediction and Saturation of water predicted by Actual and Predicted values