Lithology and Porosity Distribution of High-Porosity Sandstone Reservoir in North Adriatic Using Machine Learning Synthetic Well Catalogue

Abstract

Reservoir characterization on offshore fields often faces specific challenges due to limited or unevenly distributed well data. The object of this study is the North Adriatic poorly consolidated clastic reservoir characterized by high porosity. The seismic data indicate notable differences in reservoir quality spatially. The only two wells on the field drilled the best reservoir area. Seismic data, seismic reservoir characterization, and accurate integration with scarce well data were crucial. This paper demonstrates how the application of machine learning algorithms, specifically a Deep Forward Neural Network (DFNN), and the incorporation of pseudo-well data into the reservoir characterization process can improve reservoir properties prediction. The methodology involves creating different reservoir porosity and thickness scenarios using pseudo-well data, synthetic pre-stack seismic data generation, seismic inversion, and DFNN utilization to improve porosity prediction. This study also highlights the importance of lithology discrimination in the geological model to better constrain reservoir properties distribution in the entire reservoir volume. Facies probability analysis was utilized to define interdependence between litho–fluid classes established from the well data and acoustic impedance volume. Apart from the field well data, seismic inversion results, and DFNN porosity volume as main inputs, acknowledgments from the neighboring fields also had an important role.