Incorporate well log Information into Seismic Cube, Utilizing Probabilistic Neural Network to Generate Effective Porosity for Mishrif Formation in the H field

The enhancement of hydrocarbon production is practicable when the permeability characteristics of the reservoir can be accurately anticipated, given that there exists a strong correlation between permeability and the effect porosity of the geological formation. The porosity characteristic within carbonate reservoirs is marked by its heterogeneous and intricate nature. Seismic data offer improves laterally outcome and brightens to cover a wider area. Seismic inversion provides the representative dataset for the appreciated external seismic attributes. In practical applications, each seismic attribute is accompanied by a significant degree of interpretative uncertainty. Therefore, every singular attribute offers a distinct perspective on the seismic data. In the current study, we have predicted physical properties such as effective porosity employing an Artificial Neural Network (ANN) methodology by accomplish the EMERGE module to train the inverted 3D acoustic impedance with 3D seismic data and a well porosity log. The probabilistic Artificial neural network (PNN) exhibits a significant correlation through the actual log data, and the chosen superlative attributes reached a high correlation coefficient (0.865). The current investigation assesses the efficacy of the PNN model for predicting effect porosity, utilizing seismic attributes as a basis for analysis.