neural networks
-
This paper presents a physics-informed neural network technique able to use information from fluid-flow physics as well as observed data to model the Buckley-Leverett problem. -
The authors develop a methodology that calculates the mechanical specific energy using real-time drillstring acceleration signals directly.
-
The authors of this paper present a method for prediction of sucker-rod-pump failure based on improved, completely connected perceptron artificial neural networks.
-
This paper analyzes several configurations of convolutional neural networks suited for predicting upscaled fracture permeabilities and shape factors required to close a dual porosity/dual permeability model.
-
The paper describes an end-to-end deep surrogate model capable of modeling field and individual-well production rates given arbitrary sequences of actions.
-
The proposed solution is a good candidate for real-time burner-efficiency monitoring and automatic alarm triggering and optimization.
-
The work and the provided methodology provide a significant improvement in facies classification.
-
In the complete paper, the authors generate a model by using an artificial-neural-network (ANN) technique to predict both capillary pressure and relative permeability from resistivity.
-
Advances during the past decade in using convolutional neural networks for visual recognition of discriminately different objects means that now object recognition can be achieved to a significant extent.
-
The complete paper explores the use of multilevel derivative-free optimization for history matching, with model properties described using principal component analysis (PCA) -based parameterization techniques.
