PERMEABILITY PREDICTION FROM WELL LOGS USING AN EVOLUTIONARY NEURAL NETWORK

2002 ◽  
Vol 20 (3-4) ◽  
pp. 317-331 ◽  
Author(s):  
Alexander G. Bruce ◽  
Patrick M. Wong
Keyword(s):  
Neural Network ◽  
Well Logs ◽  
Evolutionary Neural Network ◽  
Permeability Prediction

Application of a convolutional neural network in permeability prediction: A case study in the Jacksonburg-Stringtown oil field, West Virginia, USA

Geophysics ◽  
2019 ◽  
Vol 84 (6) ◽  
pp. B363-B373 ◽  
Author(s):  
Zhi Zhong ◽  
Timothy R. Carr ◽  
Xinming Wu ◽  
Guochang Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Regression Model ◽  
Bulk Density ◽  
Carbon Storage ◽  
Oil Field ◽  
Well Logs ◽  
Storage Site ◽  
Core Samples ◽  
Permeability Prediction

Permeability is a critical parameter for understanding subsurface fluid flow behavior, managing reservoirs, enhancing hydrocarbon recovery, and sequestering carbon dioxide. In general, permeability is measured in the laboratory based on subsurface core samples, calculated from well logs or estimated from well tests. However, laboratory measurements and well tests are expensive, time-consuming, and usually limited to a few core samples or wells in a hydrocarbon field or carbon storage site. Machine-learning techniques are good options for generating a rapid, robust, and cost-effective permeability prediction model because of their strengths to recognize the potential interrelationships between input and output variables. Convolutional neural networks (CNN), as a good pattern recognition algorithm, are widely used in image processing, natural language processing, and speech recognition, but are rarely used with regression problems and even less often in reservoir characterization. We have developed a CNN regression model to estimate the permeability in the Jacksonburg-Stringtown oil field, West Virginia, which is a potential carbon storage site and enhanced oil recovery operations field. We also evaluate the concept of the geologic feature image, which is converted from geophysical well logs. Five variables, including two commonly available conventional well logs (the gamma rays [GRs] and bulk density) and three well-log-derived variables (the slopes of the GR and bulk density curves, and shale content), are used to generate a geologic feature image. The CNN treats the geologic feature image as the input and the permeability as the desired output. In addition, the permeability predicted using traditional backpropagation artificial neural networks, which are optimized by genetic algorithms and particle swarm optimization, is compared with the permeability estimated using our CNN. Our results indicate that the CNN regression model provides more accurate permeability predictions than the traditional neural network.

Permeability evaluation in a glauconite‐rich formation in the Carnarvon Basin, Western Australia

Geophysics ◽  
2000 ◽  
Vol 65 (1) ◽  
pp. 46-53 ◽  
Author(s):  
Yujin Zhang ◽  
Henry A. Salisch ◽  
Christoph Arns
Keyword(s):  
Neural Network ◽  
Prediction Models ◽  
Well Logs ◽  
Permeability Prediction ◽  
Geophysical Logs ◽  
Conventional Logs ◽  
Complex Formations ◽  
Permeability Evaluation ◽  
Petrophysical Evaluation ◽  
Carnarvon Basin

It is usually difficult for petroleum engineers and geoscientists to obtain reliable estimates of permeability from geophysical logs, especially in lithologically complex formations such as the Mardie Greensand Formation in the Carnarvon Basin, Australia, which consists of lower Cretaceous glauconite‐rich sandstones. This paper presents an alternative petrophysical evaluation of permeability in this formation through the integration of the geological and petrophysical analyses. Neural network techniques were used to establish permeability prediction models in cored wells or sections and to predict permeability from well logs in uncored wells or sections. The permeabilities obtained from minipermeameter measurements were taken as the basis and reference for the petrophysical evaluation. Four log‐derived parameters, which best reflect the permeability in the Mardie Formation, were defined and extracted from the available conventional logs. These parameters (not original log responses) were taken as the log inputs to evaluate permeability. Through the training, testing, and validation of the networks using the log and core data in the cored intervals, a permeability prediction model/network was established. Further, the permeabilities in 15 wildcat wells were determined from conventional well logs. The results indicate that the petrophysical evaluation of permeability is valid and applicable in the Mardie Formation.

Sign in / Sign up

Export Citation Format

Share Document