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 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 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.
-
The supermajor’s Energy Outlook 2025 suggests geopolitical fragmentation could tilt the balance of the energy trilemma toward energy security and away from sustainability. -
The companies said they plan to start deploying digital twin technologies in Oman this year.
-
Oil and gas experts encourage human/AI partnerships that can “supercharge” capabilities to create competitive advantages.
-
This paper reviews the motivation and development of response-based forecasting from the perspective of the authors, reviewing examples and processes that have served as validation and led to modeling refinement.
-
This paper presents a novel workflow with multiobjective optimization techniques to assess the integration of pressure-management methodologies for permanent geological carbon dioxide storage in saline aquifers.
-
This paper introduces a technology for offshore pipeline inspection centered on an autonomous robotic system equipped with underwater computer vision and edge-computing capabilities.
-
Deploying artificial intelligence across an enterprise requires thinking beyond the pilot.
-
The fifth edition of the SPE Europe Energy GeoHackathon, beginning on 1 October, focuses on how data science can advance geothermal energy and drive the energy transition.
-
This paper presents the development of a robust, physics-based, and data-driven workflow for modeling mud loss in fractured formations and predicting terminal mud loss volume and time, as well as equivalent hydraulic fracture aperture.
-
This study integrates physics-based constraints into machine-learning models, thereby improving their predictive accuracy and robustness.
