Reservoir
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 study that confirms glass-reinforced-epoxy-lined tubing as a reliable, cost-effective solution for long-term water-injection service in moderate-salinity offshore environments.
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.
-
If optimized to scale, fast fission reactors could play a role in reducing emissions in field operations by producing carbon-free electricity. -
Oil production from thin-oil-rim fields can be a challenge considering early gas breakthrough and high gas/oil ratio. This study evaluates the performance of autonomous inflow control valves (in comparison with inflow control devices and sand screens) and their effectiveness in improved oil recovery in such fields.
-
Samsung E&A takes home $6 billion of the total amount as EPC contractor.
-
As the biggest US companies grow bigger, the advantage of scale becomes clearer.
-
A 44-well development tests what ConocoPhillips has learned about maximizing the value of the wells by figuring out how they drain the reservoir.
-
Despite tens of thousands of potential candidates and the proven upsides, the unconventional industry has largely overlooked refracturing—possibly due to the way it’s discussed.
-
To avoid costly interventions like sidetracking or wellbore abandonment, a check-valve system was installed near the sandface within three injector wells which prevented the mobilization of fines from the reservoir into the wellbore by stopping backflow.
-
This year’s history matching and forecasting selections cover a deep-learning framework to forecast spatial/temporal dynamics of CO2 mineralization in reactive rocks, productivity decline analysis using coupled full-field and near-wellbore poromechanics modeling, and a reservoir graph network model for multiwell forecasting in unconventional reservoirs.
-
The authors of this paper propose a hybrid approach that combines physics with data-driven approaches for efficient and accurate forecasting of the performance of unconventional wells under codevelopment.
-
The physical characteristics of heavy oil and the formations in which it is found are often unique to a region or even to a specific asset, so recovery techniques must be tuned, adapted, and sometimes invented for each region. Creative professionals around the world are taking up this challenge and sharing their work with us in a wealth of excellent recent publication…
