|Theme||Visible||Selectable||Appearance||Zoom Range (now: 0)|
In recent years, Aker BP has explored and developed a number of digital improvements to optimize production. The underlying business drivers are meant to improve efficiency, increase production and reserves, decrease costs, and reduce the carbon footprint from operations. The example described in this article has innovative elements of digitalization and automation of workflows which provide a new approach for better handling of slugging in subsea developments with long tiebacks. The new solution has a potential for optimizing production and limiting the amount of flaring. The Aker BP-operated Vilje field in the Norwegian Continental Shelf has occasionally experienced production-flow instabilities in the production pipelines and risers due to slugging.
How time flies when you are having fun. I graduated as a mining engineer and learned my petroleum engineering on the job, initially as a Shell trainee and subsequently as a member of the SPE. Simultaneously, I learned the trade together with the soft and life skills that are critical to working with and trusting strangers. I cannot remember my first week at Shell's head-office in The Hague. But, by the weekend, I was in the small Dutch community of Zuidlaren with a rented bike checking out the best route from the hotel to my first land rig experience.
Kausik, Ravinath (Schlumberger-Doll Research) | Prado, Augustin (Schlumberger-Doll Research) | Gkortsas, Vasileios-Marios (Schlumberger-Doll Research) | Venkataramanan, Lalitha (Schlumberger-Doll Research) | Datir, Harish (Schlumberger) | Johansen, Yngve Bolstad (AkerBP)
The computation of permeability is vital for reservoir characterization because it is a key parameter in the reservoir models used for estimating and optimizing hydrocarbon production. Permeability is routinely predicted as a correlation from near-wellbore formation properties measured through wireline logs. Several such correlations, namely Schlumberger-Doll Research (SDR) permeability and Timur-Coates permeability models using nuclear magnetic resonance (NMR) measurements, K-lambda using mineralogy, and other variants, have often been used, with moderate success. In addition to permeability, the determination of the uncertainties, both epistemic (model) and aleatoric (data), are important for interpreting variations in the predictions of the reservoir models. In this paper, we demonstrate a novel dual deep neural network framework encompassing a Bayesian neural network (BNN) and an artificial neural network (ANN) for determining accurate permeability values along with associated uncertainties. Deep-learning techniques have been shown to be effective for regression problems but quantifying the uncertainty of their predictions and separating them into the epistemic and aleatoric fractions is still considered challenging. This is especially vital for petrophysical answer products because these algorithms need the ability to flag data from new geological formations that the model was not trained on as “out of distribution” and assign them higher uncertainty. Additionally, the model outputs need sensitivity to heteroscedastic aleatoric noise in the feature space arising due to tool and geological origins. Reducing these uncertainties is key to designing intelligent logging tools and applications, such as automated log interpretation. In this paper, we train a BNN with NMR and mineralogy data to determine permeability with associated epistemic uncertainty, obtained by determining the posterior weight distributions of the network by using variational inference. This provides us the ability to differentiate in- and out-of-distribution predictions, thereby identifying the suitability of the trained models for application in new geological formations. The errors in the prediction of the BNN are fed into a second ANN trained to correlate the predicted uncertainty to the error of the first BNN. Both networks are trained simultaneously and therefore optimized together to estimate permeability and associated uncertainty. The machine-learning permeability model is trained on a “ground-truth” core database and demonstrates considerable improvement over traditional SDR and Timur-Coates permeability models on wells from the Ivar Aasen Field. We also demonstrate the value of information (VOI) of different logging measurements by replacing the logs with their median values from nearby wells and studying the increase in the mean square errors.
Electromagnetic (EM) inversion processing of ultradeep resistivity data has advanced from one dimensional (1D) to three dimensional (3D). These advances have helped improve the geological complexity that can be imaged and provide additional reservoir information. The large depth of investigation (DOI) of ultradeep LWD EM tools means that distant boundaries might not be detected by any other sensor in the tool string, making it difficult to verify the results. As inversion results represent a model of the subsurface resistivity distribution and not a direct measurement, it is important to have high confidence in the results. Directly comparing the component data measured by the tool to the modeled component data from the inversion across multiple frequencies provides confidence in the resultant model where the data have a close fit. However, as measurement sensitivities decrease with distance, there is potential for non-uniqueness, generating a model that is geologically unrealistic. Increased confidence can be achieved with independent verification of the model. This paper details results from a trilateral well in an injectite reservoir wherein the sand distribution was expected to be complex. The 1D inversions showed the vertical distribution of the sand, but the results were sometimes distorted by lateral resistivity variations. The 3D inversion of the data allowed the lateral resistivity variations to be resolved. These results can be corroborated by direct comparison with azimuthal resistivity images. Additionally, the laterals all diverged from the same main bore and remained close together initially in an area containing major sand injectites. The 3D inversions from two of the wells overlap and define similarly shaped structures, providing confidence in the 3D inversion model. In complex geobodies, such as the injectites described, significant lateral variation in the reservoir distribution is expected, which is not captured by 1D inversion. Understanding the shape of these structures and their potential connectivity using 3D inversion provides a major increase in reservoir understanding that is critical to completion design.
The coronavirus crisis had a devastating effect on oil-company revenues, but it's posed a tough human-resources problem too: how to keep workers safe on cramped rigs at sea where social-distancing is impossible. Many operators have found an answer in technology--specifically, digital twins. These interactive 3D simulations of oil platforms and plants allow engineers to avoid toiling for weeks in the sweaty, close confines of a wind-battered rig, instead gaining virtual access from home. Digital twins aren't a new idea, but advances in computing--and widespread coronavirus restrictions--have helped them go mainstream in the oil industry, where the pandemic has swept through teams of engineers working elbow-to-elbow offshore. "COVID-19 has been a catalyst for this type of digital innovation," said Mitch Flegg, chief executive officer of Serica Energy, which is using the system at one of its North Sea fields.
Often located hundreds of miles away from land, offshore oil and gas platforms pose challenges with their unsheltered maritime environment, heavy weather, and risk of explosive, toxic, and corrosive atmospheres--with limited resources. Sounds like conditions are ripe for robots on rigs. In 14 years at Equinor, robotics researcher Anders Røyrøy has explored the application of robots in jobs that he describes as "dangerous, dirty, distant, or dull," where use of a robot can serve to mitigate or eliminate safety risks for humans. One of the highest priorities for robotic development and deployment, in view of their impact on inspection and maintenance routines, are remote operators for onshore and offshore platforms. Failures in such harsh environments could jeopardize the lives of human operators, the environment, and process equipment.
Carlo Caso is in charge of products in subsurface and drilling, overseeing the roadmap of the Cognite Data Fusion core components and applications to deliver value across exploration, field development, and drilling. He has more than 15 years of international experience in both domain and technology roles related to subsurface and drilling, serving both academia and the energy industry. After earning his PhD in geology, Caso led projects aimed at the exploration and development of geothermal and oil and gas resources in diverse areas across Europe and North and South America. In the past 7 years, working for Schlumberger, he has gained expertise in subsurface and drilling software technology. In 2017, he earned an executive MBA, strengthening his expertise in the transformational change driven by digital technologies.
Mark Rubin is responsible for overall management of SPE. He works with the Board of Directors and senior staff to develop strategic and business plans and formulate the organization's goals, objectives, policies, and programs. He also organizes and directs the global staff organization, which includes offices in Dallas, Houston, Calgary, Kuala Lumpur, Dubai, London, and Moscow, to ensure the accomplishment of SPE's mission. He was appointed executive director of SPE in August 2001. Prior to this appointment, he served as upstream general manager for the American Petroleum Institute (API) in Washington, D.C.
Just a few months into a new decade and the impact of the COVID-19 pandemic, combined with oil market turmoil, is causing undeniable concern for the wellbeing of the workforce and future oil and gas operations. Now, more than ever, safely managing the role of digitalization and demand for decarbonization, while efficiently balancing the books, will be critical for companies to survive and thrive. At the core of such an evolution are the people who drive the industry forward to deliver safer, cleaner, and more efficient energy to the world. The industry's economics have shifted significantly, and we will be grappling with challenges for some time. New ways of working that leverage the right mix of talent and technologies will be more important than ever as we look toward the future.