We illustrate novel application of Machine Learning (ML) assisted fault interpretation in the Middle East, interpreting complex fault structures with subtle throws in a large carbonate field onshore Abu Dhabi. Introduced as part of an integrated multi-disciplinary digital excellence initiative at ADNOC, ML-assisted fault interpretation seeks to overcome historic operational bottlenecks caused by traditional seismic interpretation methods which are slow, labour intensive, repetitive, and subjective. Core objectives for deploying ML-assisted fault interpretation were to reduce evaluation time, improve interpretation accuracy, and ensure integration across an intelligent evaluation ecosystem comprised of various disciplines. Envisaged gains from deploying ML-assisted fault interpretation methodology included effective and efficient utilization of multiple seismic datasets to drive rapid multi-scenario analysis, leading to better subsurface understanding within much shorter time frames. Input data used of the project was standard amplitude volume with minimal user-end conditioning. PSTM time and PSDM depth seismic volumes were used in separate runs to confirm that applied ML technology is domain agnostic. The ML-Assisted workflow included: Generating a fault prediction cube based on user-supplied fault interpretation labels made on 6 training lines (<0.8% of the available lines); Creation of fault planarity and azimuth cubes; Parameterization of automated extraction function; Extraction of segmented 3D fault pointsets; Creation of fault framework and fault sticks that can be integrated into traditional methods in seismic and geological modelling domains. Despite limited fault displacement apparent on the seismic volumes, ML fault predictions were of high quality, closely adhering to the seismic response as guided by user-provided training samples. Advantages envisaged from use of ML-assisted interpretation technology in the project were fully realized as the technology enabled rapid extraction of complicated fault structures within a fraction of the time and effort previously taken using traditional means. Efficiency and precision gains from using ML-assisted fault interpretation presents benefits that single seismic volumes can be evaluated thoroughly, and multiple seismic datasets (e.g. various azimuthal volumes) can be evaluated consistently for multi-scenario analysis to reduce subsurface risk and inform better decisions at all phases of the E&P Asset lifecycle.
This paper highlights 3D reconstruction of the paleo-topography of the depositional environment for a Lower Cretaceous carbonate formation onshore Abu Dhabi using 3D seismic and well data. The reconstruction was carried out for two reasons: (1) to understand underlying geologic causes for anomalous lateral variations in pressure, production performance, and logged reservoir properties in the field and (2) to delineate geologic trends away from well control in order to guide further decisions on field development and reservoir management options. Present-day structure of the reservoir top is a high-relief elongated anticline that is open to neighboring giant oil fields. Known hydrocarbon contact is below structural spill-point between the field and its neighbors, however pressure and production data indicate that the field is isolated from its neighbors. No fault was seen on seismic separating the field from its neighbors, thus raising possibility of stratigraphic separation. Further, study on core samples indicated that reservoir quality is controlled by depositional facies and early diagenetic modifications thereof. Thus, reconstruction of paleo-structure was conceived as a means of understanding and delineating geologic drivers for lateral variations in reservoir quality. The reconstruction process relied on an integrated approach: combining information from seismic, well logs, sedimentology, and well test results. Sedimentology studies gave information on expected morphology of depositional environment and controlling factors for reservoir quality; seismic interpretation of structure and stratigraphy at several levels provided basis to understand present-day field architecture and structural evolution through geologic time; reconstruction of three-dimensional structure at time of deposition was achieved by means of restorative velocity models to translate input mapped surfaces to their approximate original morphologies; results validation was achieved by subjecting study outputs to conformance tests with independent data from well logs, pressure tests, production performance, and seismic attributes trends. After reconstruction carried out in this study, the present-day steep anticlinal structure at the target reservoir was translated to a gently dipping ramp with morphology that is consistent with interpreted environment of deposition from cores. Outputs were further validated by conformance of well data and seismic attribute trends with the paleo-structure. Anomalous lateral variations in reservoir properties measured in wells were found to be associated with possible tidal channels that were interpreted to have caused localized diagenetic changes. Thus, findings from the paleo-reconstruction study provided a geologically consistent framework to understand lateral variation in well results, and also provided basis to guide further field development and reservoir management decisions as intended at study inception. Although outputs from the paleo-reconstruction process used in this study were deemed to have given good results, potential pitfalls in applying the method are herein noted.
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.