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

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. seismic data indicate notable differences in quality spatially. only two wells field drilled best area. Seismic data, characterization, and accurate integration with scarce were crucial. This paper demonstrates how application machine learning algorithms, specifically a Deep Forward Neural Network (DFNN), incorporation pseudo-well into process can improve properties prediction. methodology involves creating different porosity thickness scenarios using synthetic pre-stack generation, inversion, DFNN utilization also highlights importance lithology discrimination geological model better constrain distribution entire volume. Facies probability analysis was utilized define interdependence between litho–fluid classes established from acoustic impedance Apart inversion results, volume as main inputs, acknowledgments neighboring had an important role.