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.
-
Large geological models are needed for modeling the subsurface processes in geothermal, carbon-storage, and hydrocarbon reservoirs. The size of these models contributes to the computational cost of history matching, engineering optimization, and forecasting. To reduce this cost, low-dimensional representations need to be extracted. Deep-learning tools, such as autoenc… -
The new Methane Alert and Response System initiative aims to scale up global efforts to detect and act on major emission sources in a transparent manner and accelerate implementation of the UN’s Global Methane Pledge. The system is designed to alert governments, companies, and operators about large methane sources to aid rapid mitigation.
-
Methods inspired by artificial intelligence and software development help generate more ideas that add more value.
-
Feeding better battery storage with the energy produced by cleaner sources such as solar panels and wind turbines is not a new idea. But are good ideas enough? Or could AI be the answer to unlocking the true value of the next generation of solar and energy innovations?
-
This paper shares details of 2 years of monitoring the first commingled updip smart water injector drilled in the Piltun area of the Piltun-Astokhskoye offshore oil and gas field.
-
A consortium of 20 organizations, REX-CO2, including research institutions, operators, and regulatory authorities, studied mature wells in two areas of the UK Continental Shelf. Subsurface data were evaluated and verified the wells’ potential suitability for both reuse and CO2 injection and storage.
-
This paper discusses a waterflood optimization system that provides monitoring and surveillance dashboards with artificial-intelligence and machine-learning components to generate and assess insights into waterflood operational efficiency.
-
At the company’s annual conference, leaders from its Automations Solutions business laid out a three-pronged effort to improve automation architecture—intelligent fields, the edge, and the cloud.
-
So far, digital twins have focused mainly on mimicking small, well-defined systems. Integrated asset models, however, tend to address the bigger picture. In this video, Distinguished Lecturer Kristian Mogensen addresses whether we can take the best from both worlds, whether we need to, and how to go about developing such a technical solution.
-
SponsoredWhy oil and gas companies can’t get the data they need for production optimization (and how to change that).
