Data & Analytics
This research focuses on combining physics-based expert rules with machine learning to improve the detection of failure-related events in electrical submersible pumps.
A combination of physics principles and machine-learning techniques is used in this work to develop a virtual flowmeter for oil-production optimization in electrical-submersible-pump-lifted oil wells, resulting in reliable generalization.
This paper presents the deployment of an artificial intelligence-enabled autonomous gas lift optimization system, integrating real-time centralized advanced process control with cloud-based analytics to enhance artificial gas lift performance in producer wells.
-
With so much volatility in the sector, acutely felt by many western consumers, how are intelligent work flows enabling the shift toward alternatives? -
Among other things, Microsoft is making it possible for Exxon to analyze reams of oilfield data. Amazon is helping drillers run simulations to maximize how much oil they can pump from existing wells.
-
Trials of the robotics company’s Hydronaut and Aquanaut system are expected in the third quarter of 2022 after the companies conducted a successful feasibility study.
-
The Russian gas company announced that it will use locally source unmanned aerial vehicles to inspect its facilities and pipelines in the Yurkharovskoye field.
-
Incorporating domain knowledge into your architecture and your model can make it a lot easier to explain the results, both to yourself and to an outside viewer. Every bit of domain knowledge can serve as a stepping stone through the black box of a machine learning model.
-
The COVID-19 pandemic caused a major disruption to industry training programs and university geoscience courses as travel restrictions and lockdowns created the need for digital alternatives. Although virtual field trips had been gaining traction before the pandemic, the sudden need to replace physical field activities has driven a rising interest to allow geologists …
-
This paper presents a work flow that has been applied to crossdipole sonic data acquired in a vertical pilot well drilled in the Permian Basin.
-
This paper describes a new intelligent dosing technology to reduce liquid loading in an unconventional tight gas reservoir.
-
This paper presents a mathematical analysis of how incorrect estimates of initial reservoir pressure may affect rate-transient analysis in ultralow-permeability reservoirs.
-
In this work, novel physics-based models and machine-learning models are presented and compared for estimating permanent-downhole-gauge measurements.
