AI/machine learning
The grant was awarded by the Scottish Funding Council in partnership with Scottish Enterprise to assist in developing an AI demonstrator to optimize subsea decommissioning.
Chevron and ExxonMobil are working on deals to use natural gas and carbon capture to power the technology industry's AI data centers, executives with the companies said.
Undocumented orphaned wells pose hazards to both the environment and the climate. Scientists are building modern tools to help locate, assess, and pave the way for ultimately plugging these forgotten relics.
-
This paper presents the processes of identifying production enhancement opportunities, as well as the methodology used to identify underperforming candidates and analyze well-integrity issues, in a brownfield offshore Malaysia. -
This paper delves into the evolving landscape of drilling automation, emphasizing the imperative for these systems to go beyond novelty and deliver quantifiable financial value.
-
This paper presents a workflow that combines probabilistic modeling and deep-learning models trained on an ensemble of physics models to improve scalability and reliability for shale and tight-reservoir forecasting.
-
This paper describes a new application that leverages advanced machine-learning techniques in conjunction with metocean forecasts to predict vessel motions and thruster loads.
-
The industry’s vast untapped data resources have the potential to change how our industry works—if we can piece it together.
-
New and evolving artificial lift technology is helping operators improve production rates.
-
Collaboration and technology will help the industry meet its toughest challenges, experts said during the opening session at ATCE.
-
Accuracy, complexity, costs, and skills availability may make it difficult to get the most out of digital twins and even potentially misrepresent or miss actual changes in the status of systems or facilities.
-
The new contract extends a decadelong relationship and expands the use of AI and digital twins.
-
This paper presents a novel modeling framework for predicting residual oil saturation in carbonate rocks. The proposed framework uses supervised machine learning models trained on data generated by pore-scale simulations and aims to supplement conventional coreflooding tests or serve as a tool for rapid residual oil saturation evaluation of a reservoir.
