AI/machine learning
The deals, with a potential value exceeding $3.7 billion, are aimed at strengthening Saudi Aramco’s supply chains and expanding its use of industrial artificial intelligence.
This work applies fuzzy logic, a well-established artificial-intelligence technique, to quantitatively assess connectivity between injectors and producers in a giant presalt field in the Santos Basin of Brazil.
The DOE-backed EGS-Twin project aims to simulate geothermal production systems, helping operators better predict performance and maximize output.
-
The paper describes an approach to history matching and forecasting that does not require a reservoir simulation model, is data driven, and includes a physics model based on material balance. -
The collaboration is planned to explore artificial intelligence in an effort to get more value from oil and gas operations and create a sustainable and carbon-efficient future for the energy industry.
-
Accenture research suggests that only 12% of companies have advanced their AI maturity enough to achieve superior growth and business transformation. These companies are "AI Achievers" and, on average, attribute 30% of their total revenue to AI.
-
Their model’s predictions should help researchers improve ocean climate simulations and hone the design of offshore structures.
-
The paper describes the experience of using a machine-learning model prepared by the ensemble method to prevent stuck-pipe events during well construction in extended-reach wells.
-
This paper presents the development and test of a method to predict upstream events that could lead to flaring, applying an integrated framework using machine-learning and big-data analytics.
-
A field test conducted by Yokogawa Electric and JSR resulted in a chemical plant being run autonomously for the first time by artificial intelligence for 35 days.
-
C3 AI reported that the oil major has hit the milestone of 10,000 pieces of equipment being monitored by its predictive-maintenance artificial intelligence.
-
This paper describes a novel machine-learning approach for processing distributed fiber-optic sensing data that enables dynamic flow-profile monitoring using a fiber-optic electric-line cable deployed in a gas condensate well.
-
The authors describe an integrated multiscale data methodology involving machine-leaning tools applied to the Late Jurassic Upper Jubaila formation outcrop data.
