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.
-
The SPE Reservoir Technical Discipline and Advisory Committee invite their Reservoir members worldwide to participate in a new survey aimed at assessing the current state of reservoir engineering across industry and academia. Deadline is 21 July 2025. -
This paper presents a fundamental research study with the main objective of building a mechanistic numerical model that captures the important mechanisms of polymer flooding through various mechanistic equations using a combined reservoir flow and geochemical numerical simulator.
-
The authors of this paper describe reservoir-fluid-geodynamics processes that explain the reasons behind varying oil compositions and properties within and across different reservoir compartments.
-
In this study, a deep-neural-network-based workflow with enhanced efficiency and scalability is developed for solving complex history-matching problems.
-
This study presents a production-optimization method that uses a deep-learning-based proxy model for the prediction of state variables and well outputs to solve nonlinearly constrained optimization with geological uncertainty.
-
In this work, a perturbed-chain statistical associating fluid theory equation of state has been developed to characterize heavy-oil-associated systems containing polar components and nonpolar components with respect to phase behavior and physical properties.
-
The paper describes a parameter inversion of reservoirs based on featured points, using a semi-iterative well-test-curve-matching approach that addresses problems of imbalanced inversion accuracy and efficiency.
-
This paper introduces a novel optimization framework to address CO2 injection strategies under geomechanical risks using a Fourier neural operator-based deep-learning model.
-
The authors introduce a novel framework combining dynamic mode decomposition, a data-driven model-reduction technique, with direct data assimilation to streamline the calibration of carbon-dioxide plume evolution models.
-
This paper discusses the concept, applications, and continual evolution of a new 3D temperature and spectral-acoustics modeling and logging approach.
