Reservoir simulation
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.
-
A new program offers an affordable way to figure out if salt precipitation could be behind underperforming gas wells and suggests a path to higher production. -
Artificial intelligence (AI) and machine learning (ML) technologies have rapidly progressed and have significantly affected traditional reservoir engineering, bringing innovative methodologies to reservoir simulations. However, it is essential to understand that these AI and ML technologies are only as effective and trustworthy as the data they are trained on.
-
This paper describes a work flow that integrates data analysis, machine learning, and artificial intelligence to unlock the potential of large relative permeability databases.
-
The objective of this study was to establish an efficient optimization work flow to improve vertical and areal sweep in a sour-gas injection operation, thereby maximizing recovery under operation constraints.
-
The objective of this paper is to present a fundamentals-based model of three-phase flow consistent with observation that avoids the pitfalls of conventional models such as Stone II or Baker’s three-phase permeability models.
-
In an industry where methane leaks and carbon dioxide storage are increasingly important concerns, finding new ways to seal leaks is a valuable skill.
-
Several options exist for large-scale hydrogen underground storage: lined caverns, salt domes, saline aquifers, and depleted oil/gas reservoirs. In this paper, a commercial reservoir simulator was used to model cyclic injection/withdrawal from saline aquifers and depleted oil/gas reservoirs. The results revealed the need to contain the stored volume with an integrated…
-
The authors of this paper present an approach integrating characterization of paleo zones, parameterization of paleo-zone conductivity, and application of flow profiles in a history-matching study of a dual-porosity/dual-permeability model.
-
The authors of this paper develop a robust history-matched reservoir simulation model capable of predicting polymerflooding performance in the first such pilot to enhance heavy oil recovery on Alaska’s North Slope.
-
One of the more common characteristics of heavy oil reservoirs is a low primary recovery factor, which is mainly because of unfavorable mobility ratios between oil and water, negligible solution drives, and faster decline of reservoir pressures because of relatively low oil compressibility. Most of the technologies that apply to heavy oil reservoirs need to address th…
