Data & Analytics
With the latest addition, the Italian major’s computational capacity passes the exaflop threshold, making the firm the world’s leading company by computing power in the new TOP500 global ranking.
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.
-
New research led by the University of Glasgow’s School of Psychology and Neuroscience presents an approach to understand whether the human brain and deep neural networks recognize things in the same way. -
As we continue to reduce our reliance on fossil fuels, we risk becoming more vulnerable if we don’t start associating climate resiliency with cyber resiliency.
-
Founded by former analytics experts for a large US independent, Xecta Digital Labs is proposing a new analysis method for horizontal wells. Adopting it means turning the page on some old habits.
-
The authors of this paper develop a model that can predict well-risk level and provide a method to convert associated failure risk of each element in the well envelope into a tangible value.
-
This paper presents agile technologies that integrate data management, data-quality assessment, and predictive machine learning to maximize asset value using underused legacy core data.
-
The authors write that child-well performance increases with spacing and decreases with infill timing and that the parent cumulative production at child-well completion is an effective indicator of child-well performance.
-
The authors of this paper propose a novel approach to data-driven modeling for transient production of oil wells.
-
A just-launched publicly available database translates reserves and production data into greenhouse-gas emissions as CO2 equivalents. It was built using data from more than 50,000 fields in 89 countries, which covers about 75% of global reserves, production, and emissions.
-
Digital systems are helping ensure US independent Diversified Energy continues to grow and optimize production from its mature assets.
-
Schlumberger and Cognite have partnered to integrate Schlumberger’s Enterprise Data Solution for subsurface with Cognite Data Fusion, Cognite’s open industrial DataOps platform.
