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.
-
These papers provided insights and advances into field-operations automation, machine-learning-assisted petrophysical characterization, and fluid-distribution analysis in unconventional assets. -
In this paper, the authors propose a regression machine-learning model to predict stick/slip severity index using sequences of surface measurements.
-
From optimizing drilling performance to enhancing worker safety, computer vision can change how the industry works.
-
A recent survey conducted by Rackspace Technology reveals new attitudes about using the cloud, including a change from using the public cloud to using private, on-site clouds or a hybrid of the two.
-
This study examines the implementation of a predictive maintenance method using artificial intelligence and machine learning for offshore rotating production-critical equipment. Conducted over 2 years at Murphy Oil’s deepwater platforms in the Gulf of Mexico, the project aimed to detect equipment issues early, reduce downtime, and streamline maintenance processes.
-
Moving from use cases to enterprisewide AI is more than a technology challenge. It requires anchoring on value, feedback, and innovation.
-
This paper focuses on the vital task of identifying bypassed oil and locating the remaining oil in mature fields, emphasizing the significance of these activities in sustaining efficient oilfield exploitation.
-
The objective of this study is to develop an explainable data-driven method using five different methods to create a model using a multidimensional data set with more than 700 rows of data for predicting minimum miscibility pressure.
-
The authors present an open-source framework for the development and evaluation of machine-learning-assisted data-driven models of CO₂ enhanced oil recovery processes to predict oil production and CO₂ retention.
-
The authors of this paper propose hybrid models, combining machine learning and a physics-based approach, for rapid production forecasting and reservoir-connectivity characterization using routine injection or production and pressure data.
