|Theme||Visible||Selectable||Appearance||Zoom Range (now: 0)|
Kazak, Andrey (Center for Hydrocarbon Recovery, Skolkovo Institute of Science and Technology) | Simonov, Kirill (Center for Hydrocarbon Recovery, Skolkovo Institute of Science and Technology) | Kulikov, Victor (PicsArt Inc. and Skolkovo Institute of Science and Technology)
Summary The modern focused ion beam-scanning electron microscopy (FIB-SEM) allows imaging of nanoporous tight reservoir-rock samples in 3D at a resolution up to 3 nm/voxel. Correct porosity determination from FIB-SEM images requires fast and robust segmentation. However, the quality and efficient segmentation of FIB-SEM images is still a complicated and challenging task. Typically, a trained operator spends days or weeks in subjective and semimanual labeling of a single FIB-SEM data set. The presence of FIB-SEM artifacts, such as porebacks, requires developing a new methodology for efficient image segmentation. We have developed a method for simplification of multimodal segmentation of FIB-SEM data sets using machine-learning (ML)-based techniques. We study a collection of rock samples formed according to the petrophysical interpretation of well logs from a complex tight gas reservoir rock of the Berezov Formation (West Siberia, Russia). The core samples were passed through a multiscale imaging workflow for pore-space-structure upscaling from nanometer to log scale. FIB-SEM imaging resolved the finest scale using a dual-beam analytical system. Image segmentation used an architecture derived from a convolutional neural network (CNN) in the DeepUNet (Ronneberger et al. 2015) configuration. We implemented the solution in the Pytorch® (Facebook, Inc., Menlo Park, California, USA) framework in a Linux environment. Computation exploited a high-performance computing system. The acquired data included three 3D FIB-SEM data sets with a physical size of approximately 20 × 15 × 25 µm with a voxel size of 5 nm. A professional geologist manually segmented (labeled) a fraction of slices. We split the labeled slices into training, validation, and test data. We then augmented the training data to increase its size. The developed CNN delivered promising results. The model performed automatic segmentation with the following average quality indicators according to test data: accuracy of 86.66%, precision of 54.93%, recall of 83.76%, and F1 score of 55.10%. We achieved a significant boost in segmentation speed of 14.5 megapixel (MP)/min. Compared with 0.18 to 1.45 MP/min for manual labeling, this yielded an efficiency increase of at least 10 times. The presented research work improves the quality of quantitative petrophysical characterization of complex reservoir rocks using digital rock imaging. The development allows the multiphase segmentation of 3D FIB-SEM data complicated with artifacts. It delivers correct and precise pore-space segmentation, resulting in little turn-around-time saving and increased porosity-data quality. Although image segmentation using CNNs is mainstream in the modern ML world, it is an emerging novel approach for reservoir-characterizationtasks.
Temizel, Cenk (Saudi Aramco) | Canbaz, Celal Hakan (Ege University) | Gok, Ihsan Murat (NESR) | Roshankhah, Shahrzad (Caltech) | Palabiyik, Yildiray (ITU) | Deniz-Paker, Melek (Independent Consultant) | Hosgor, Fatma Bahar (Petroleum Software LLC) | Ozyurtkan, Hakan (ITU) | Aksahan, Firat (Ege University) | Gormez, Ender (METU) | Kaya, Suleyman (METU) | Kaya, Onur Alp (METU)
Abstract As major oil and gas companies have been investing in shale oil and gas resources, even though has been part of the oil and gas industry for long time, shale oil and gas has gained its popularity back with increasing oil prices. Oil and gas industry has adapted to the low-cost operations and has started investing in and utilizing the shale oil sources significantly. In this perspective, this study investigates and outlines the latest advances, technologies, potential of shale oil and gas reservoirs as a significant source of energy in the current supply and demand dynamics of oil and gas resources. A comprehensive literature review focusing on the recent developments and findings in the shale oil and gas resources along with the availability and locations are outlined and discussed under the current dynamics of the oil and gas market and resources. Literature review includes a broad spectrum that spans from technical petroleum literature with very comprehensive research using SCOPUS database to other renowned resources including journals and other publications. All gathered information and data are summarized. Not only the facts and information are outlined for the individual type of energy resource but also the relationship between shale oil/gas and other unconventional resources are discussed from a perspective of their roles either as a competing or a complementary source in the industry. In this sense, this study goes beyond only providing raw data or facts about the energy resources but also a thorough publication that provides the oil and gas industry professional with a clear image of the past, present and the expected near future of the shale oil/gas as it stands with respect to other energy resources. Among the few existing studies that shed light on the current status of the oil and gas industry facing the rise of the shale oil are up-to-date and the existing studies within SPE domain focus on facts only lacking the interrelationship between heavy and light oil as a complementary and a competitor but harder-to-recover form of hydrocarbon energy within the era of rise of renewables and other unconventionals. This study closes the gap and serves as an up-to-date reference for industry professionals.