Digital Oil Field
This work describes a study in which distributed data parallel training, paired with a node-local caching pipeline, enabled efficient multigraphics-processing-unit scaling for a CO₂-storage graph-neural-network surrogate while maintaining generalization.
This paper presents a novel reservoir engineering/reservoir simulation approach—a data-driven interwell-connectivity model augmented as a digital twin—to predict reservoir dynamics and optimize operations in the Changqing oil field of China.
This work uses a novel pseudosteady-state-based simulation to reduce training-data-generation cost while maintaining high-performance predictions of data-driven proxy models for carbon-sequestration projects.
-
Two new centers in Bergen, Norway will lean on emerging digital technology to oversee much of the Norwegian operator’s offshore operations. -
Companies are bringing satellite monitoring to the unconventional oilfield—namely the Permian Basin—where they are training machine learning models to track and predict drilling and completions work.
-
Discussions of big data and its management are increasing across our industry and disciplines. This selection of technical papers takes a look at data mining, the ethical issues associated with it, and the status of data-driven methods.
-
Remote condition monitoring of offshore platform equipment tracks performance data, watching for deviations from baseline benchmarks. Unexpected variances can be investigated and serviced by technicians dispatched to target the root causes—an approach called condition-based maintenance.
-
“Greedy pursuit” in the realm of algorithms is a good thing. Saudi Aramco studied such algorithms to produce images simulating the flow inside a pipe’s cross section, possibly reducing the need for separator-based multiphase flowmeters.
-
Predicting the trajectory of a satellite, or a well, requires sophisticated analysis to reduce the huge uncertainties. That adds to the many things drillers should be thinking about, which can be overwhelming.
-
These days, it is all about digital. Click to find out what industry leaders from Encana, Google, Schlumberger, and Shell have to say about the ongoing transformation towards data-driven profitability.
-
The data collected via monitoring and metering applications are increasingly viewed as central to assessing production performance and in decision making to optimize field development and operations.
-
Having blockchain on an oil rig means everyone on the job shares a view of a project from start to finish. This could facilitate innovations that cut costs, but organizational change is required.
-
The objective of this paper is to illustrate a methodology for identifying the value of information (VOI) in reservoir management—in particular, for deriving the conditional probabilities of success when new and imperfect data are acquired.
