AI/machine learning
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.
-
This paper presents the first global application of autonomous drilling in deepwater and the journey to reach optimal drilling parameters, integrating proprietary tools from the project’s business partners. -
In this paper, a case study is described in which a software solution enabled prescriptive optimization of well delivery using a physics-informed machine-learning approach for predictive identification and characterization of well-construction risks.
-
The companies also agreed to collaborate on new AI models to unlock further insights from S&P Global Energy’s upstream data.
-
As AI drives record heat loads in data centers, immersion liquid cooling is gaining momentum, and energy companies are lining up to support it.
-
Artificial intelligence is prompting oil and gas companies to redefine roles, rethink trust, and rework operations, experts said during CERAWeek.
-
The gap between machine learning research and effective deployment in the oil and gas industry is an alignment challenge between research questions and real decisions, between model design and operational constraints, and between innovation and the people expected to use it.
-
Technology and partnerships remain important, while phased approaches may supplant lengthy appraisal programs, experts said during CERAWeek.
-
CERAWeek panelists see AI as a way to leverage data and people in interpreting data for exploration, but a cultural shift at companies may still be needed.
-
This paper describes an approach to creating a digital, interconnected workspace that aligns sensor data with operational context to place the completions engineer back into a central role.
-
The authors propose a deep-learning-based approach enabling near-real-time CO2-plume visualization and rapid data assimilation incorporating multiple geological realizations for predicting future CO2 plume evolution and area-of-review determination.
