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.
The idea and interest of studying the unconventional hydrocarbon reservoirs in the Panonian Basin System, abbr. PBS, (the Drava, Mura and Zala Depressions) are achieved by defining the joint research project carried out by the multidisciplinary team of MOL and INA petroleum companies. This analysis is performed in the Croatian part of the Panonian Basin System (CPBS). Eight areas with potential existence of unconventional reservoirs were examined with focus on Tight Gas Sands and Gas Shales. The primary object in this project stage is the estimation of possible unconventional reserves of gas (or Original Gas in Place, abbr. OGIP). Reserves are defined by area and reservoir porosity, saturation and net pay. They are usually estimated from well logging data and core laboratory and hydrodynamic data. Some difficulties and inabilities of accurate, i.e. professionally acceptable reservoir evaluation, were noticed. The reason is inadequate or incomplete well logging suite and inadequate formation evaluation work flow. Therefore, evaluation concepts from unconventional reservoirs presented in North American petroleum provinces could not be directly applied in our case. It was inevitable to use other data source, especially the Mud Logging Data to quantify net pay and qualify saturation. The rate of penetration, abbr. ROP, gas indications while drilling, the presence of hydrocarbon in rock samples, fracture systems on cores, inflows, eruptions and mud losses as well as the interpretation of overpressure using D exponent, abbr. Dcs method, significantly facilitated the evaluation of necessary parameters. It is crucial to improve economics of hydrocarbon production from any basin through operational efficiency, well productivity as well as new analytical models. Here presented evaluation method of potential hydrocarbon reserves is applicable in any similar case. It provides a highly acceptable professional credibility and can be very useful in situations with incomplete and inadequate Well Logging Suite facilitating identification and categorization of unconventional reservoirs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.