AI/machine learning
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 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 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.
-
This paper describes an approach that combines rock typing and machine-learning neural-network techniques to predict the permeability of heterogeneous carbonate formations accurately. -
This study describes the performance of machine-learning models generated by the self-organizing-map technique to predict electrical rock properties in the Saman field in northern Colombia.
-
Implemented for the first time offshore, the technology uses artificial intelligence to operate wells autonomously.
-
The planned long-term partnership aims to digitally transform Aker BP’s subsurface workflows in an effort to lower costs, shorten planning cycles, and increase production.
-
This paper outlines how one company uses digital technologies to manage HSE risks in project delivery, developing an artificial intelligence (AI) predictive model to predict HSE risks and incidents based on historical incident data.
-
The RoboWell technology for well control will be available globally through Halliburton’s Landmark iEnergy hybrid cloud.
-
Automated workflow unifies geological, completion, and production data to inform speedier, better investment decisions for nonoperated assets.
-
The authors of this paper review the advantages of machine learning in complex compositional reservoir simulations to determine fluid properties such as critical temperature and saturation pressure.
-
Both new and old vessels are benefiting from automation processes that can improve operational efficiency, predict downtime, and debottleneck workflows using a flurry of crucial data points.
-
Operators tell an audience at the Unconventional Resources Technology Conference how a hybrid expandable liner system and machine-learning-based analysis improve the bottom line.
