Application of Artificial Intelligence to Characterize Naturally Fractured Reservoirs

Ouahed, Abdelkader Kouider El; Tiab, Djebbar; Mazouzi, A.

doi:10.2118/2005-055

Cited by 4 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fuzzy Logical rules are used to analyze noise signals and to select the variables for improving forecasting capabilities of ANN models. Further, in [33], both AI technologies are used to characterize fractured reservoirs, due to their capacity to manage high data volumes, and to identify relationships among variables.…”

Section: Modelling Petroleum Producer Fields With Aimentioning

confidence: 99%

Combined artificial intelligence modeling for production forecast in a petroleum production field

Marco

Alzate-Espinosa

Andrés

et al. 2019

CT&F Cienc. Tecnol. Futuro

View full text Add to dashboard Cite

This paper presents the results about using a methodology that combines two artificial intelligence (AI) models to predict the oil, water and gas production in a Colombian petroleum field. By combining fuzzy logic (FL) and artificial neural networks (ANN) a novelty data mining procedure is implemented, including a data imputation strategy. The FL tool determines the most useful variables or parameters to include into each well production model. ANN and FIS (fuzzy inference systems) predictive models identification is developed after the data mining process. The FIS models are capable to predict specific behaviors, while ANN models are able to forecast an average behavior. The combined use of both tools under few iterative steps, allows to improve forecasting of well behavior until reach a specified accuracy level. The proposed data imputation procedure is the key element to correct false or to complete void positions into operation data used to identify models for a typical oil production field. At the end, two models are obtained for each well product, conforming an interesting tool given the best accurate prediction of fluid phase production.

show abstract

Section: Modelling Petroleum Producer Fields With Aimentioning

confidence: 99%

Combined artificial intelligence modeling for production forecast in a petroleum production field

Marco

Alzate-Espinosa

Andrés

et al. 2019

CT&F Cienc. Tecnol. Futuro

View full text Add to dashboard Cite

show abstract

“…This occurs mostly in the case of large networks with little available data. By dividing the data into three sets, training, testing and verification, the problem can be avoided 20…”

Section: Modelingmentioning

confidence: 99%

“…For multilayer feed‐forward neural networks, a powerful supervised learning algorithm, called back propagation, was employed to recursively adjust the connection weights so that the difference between the estimated and the observed outputs was as small as possible. The training process creates a set of parameters that can be used for estimating property values in situations where the actual output is unknown 20. Once the training process converges, the testing data set must be presented to the network.…”

Section: Modelingmentioning

confidence: 99%

Determination of bubble size distribution in a bubble column reactor using artificial neural network

Amiri

Mehrnia

Barzegari

et al. 2011

Asia-Pacific J Chem Eng

View full text Add to dashboard Cite

In the present study, bubble size distribution (BSD) within a bubble column reactor was modeled using an artificial neural network (ANN). The fluids tested in the bubble column consisted of 11 different oil mixtures, each containing two different oils. Pure water was also tested. BSD was determined for various superficial gas velocities by photographing the state of the fluid. It was found that bubble size as well as distribution depended on parameters, such as gas flow rate, liquid properties, sparger pore diameter and distance from the sparger in the column. The proposed ANN model is based on more than 4500 data points collected for BSD estimation. Through statistical testing, it was found that the model has a correlation coefficient greater than 70% and upon experimental testing was found to better predict BSD than currently used correlations found in the literature. 

show abstract

A Deep Learning Formation Image Log Classification Framework for Fracture Identification – A Study on Carbon Dioxide Injection Performance for the New Zealand Pohokura Field

Katterbauer

Qasim

Shehri

et al. 2022

SPE Annual Technical Conference and Exhibition

View full text Add to dashboard Cite

We have presented a new deep learning framework for the detection of fractures in formation image logs for enhancing CO2 storage. Fractures may represent high velocity gas flow channels which may make CO2 storage a challenge. The novel deep learning framework incorporates both acoustic and electrical formation image logs for the detection of fractures in wellbores for CO2 storage enhancement and injection optimization. The framework was evaluated on the Pohokura-1 well for the detection of fractures, with the framework exhibiting strong classification accuracy. The framework could accurately classify the fractures based on acoustic and electrical image logs in 98.1 % for the training and 85.6 % for the testing dataset. Furthermore, estimates of the fracture size are strong, indicating the ability of the framework to accurately quantify fracture sizes in order to optimize CO2 injection and storage.

show abstract

Application of Artificial Intelligence to Characterize Naturally Fractured Reservoirs

Cited by 4 publications

References 0 publications

Combined artificial intelligence modeling for production forecast in a petroleum production field

Combined artificial intelligence modeling for production forecast in a petroleum production field

Determination of bubble size distribution in a bubble column reactor using artificial neural network

A Deep Learning Formation Image Log Classification Framework for Fracture Identification – A Study on Carbon Dioxide Injection Performance for the New Zealand Pohokura Field

Contact Info

Product

Resources

About