AI/machine learning
This paper introduces an agentic artificial-intelligence framework designed for offshore production surveillance and intervention.
In the past year, publications on CO2, natural gas, and hydrogen storage have increasingly focused on the design, evaluation, and optimization of storage plans. These efforts encompass a broad spectrum of challenges and innovations, including the expansion of storage reservoirs from depleted gas fields and saline aquifers to stratified carbonate formations and heavy-o…
Reaching further than dashboards and data lakes, the agentic oil field envisions artificial intelligence systems that reason, act, and optimize.
-
This paper discusses a comprehensive hybrid approach that combines machine learning with a physics-based risk-prediction model to detect and prevent the formation of hydrates in flowlines and separators. -
This paper explains that the discovery of specific pressure trends, combined with an unconventional approach for analyzing gas compositional data, enables the detection and prediction of paraffin deposition at pad level and in the gathering system.
-
Adaptability, collaboration, and digital technologies are all pages in Aramco’s oilfield R&D playbook.
-
Industry experts dissected the challenges in deploying artificial intelligence across the energy sector during a special session at SPE’s Annual Technical Conference and Exhibition.
-
AI is transforming the field of cybersecurity, offering new possibilities and challenges for both defenders and attackers, but AI also can introduce new vulnerabilities and risks and raise new ethical, legal, and social issues for cybersecurity.
-
This paper presents a case study highlighting the demonstration, refinement, and implementation of a machine-learning algorithm to optimize multiple electrical-submersible-pump wells in the Permian Basin.
-
This paper presents a closed-loop iterative well-by-well gas lift optimization workflow deployed to more than 1,300 operator wells in the Permian Basin.
-
This paper explores the use of machine learning in predicting pump statuses, offering probabilistic assessments for each dynacard, automating real-time analysis, and facilitating early detection of pump damage.
-
This paper focuses on developing a model that can be used in an automated, end-to-end flare-smoke detection, alert, and distribution-control solution that leverages existing flare closed-circuit television cameras at manufacturing facilities.
-
This paper describes an experimentation trial deploying and operating a computer-vision system on a deepwater rig to measure drilled cuttings in real time using a remotely monitored camera system.
