Digital Oil Field
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 demonstrates how the integration of multiphysics downhole imaging with machine-learning techniques provides a significant advance in perforation-erosion analysis. -
Reaching further than dashboards and data lakes, the agentic oil field envisions artificial intelligence systems that reason, act, and optimize.
-
This paper presents a robust workflow to identify optimization opportunities in gas lift wells through real-time data analysis and a surveillance-by-exception methodology.
-
This paper introduces an agentic artificial-intelligence framework designed for offshore production surveillance and intervention.
-
The objective of this study is to field test a non-nuclear multiphase flowmeter and assess its performance under challenging operating conditions.
-
This paper presents a multifaceted approach leveraging precise rig control, physics models, and machine-learning techniques to deliver consistently high performance in a scalable manner for sliding.
-
This paper proposes a novel approach toward drilling maximum-reservoir-contact wells by integrating automated drilling and geosteering software to control the downhole bottomhole assembly, thereby minimizing the need for human intervention.
-
This paper offers an exploration into the field applications of multiphase flowmeters (MPFMs) across global contexts and the lessons learned from implementation in a smart oil field that uses several types of MPFM.
-
This paper explores the evolving role of the digital petroleum engineer, examines the core technologies they use, assesses the challenges they face, and projects future industry trends.
-
This paper describes an auto-adaptive workflow that leverages a complex interplay between machine learning, physics of fluid flow, and a gradient-free algorithm to enhance the solution of well-placement problems.
