Layer | Fill | Outline |
---|
Map layers
Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|
Fill | Stroke |
---|---|
Collaborating Authors
Abstract Rock facies are typically identified either by core analysis to provide visually interpreted lithofacies, or determined indirectly based on suites of recorded well-log data, thereby generating electrofacies interpretations. Since the lithofacies cannot be obtained for all reservoir intervals, drilled section and/or wells, it is commonly essential to model the discrete lithofacies as a function of well-log data (electrofacies) to predict the poorly sampled or non-cored intervals. The process is called predictive lithofacies classification. In this study, measured discrete lithofacies distributions (based on core data) are comparatively modeled with well-log data using two tree-based ensemble algorithms: extreme gradient boosting (XGBoost) and adaptive boosting (AdaBoost) configured as classifiers. The predicted lithofacies are then combined with recorded well-log data for analysis by an XGBoost regression model to predict permeability. The input well-log variables are log porosity, gamma ray, water saturation, neutron porosity, deep resistivity, and bulk density. The data are derived from the Mishrif carbonate reservoir in a giant southern Iraqi oil field. For efficient lithofacies classification and permeability modelling, random sub-sampling cross-validation was applied to the well-log dataset to generate two subsets: training subset for model tuning; and testing subset for prediction of data points unseen during training of the model. Confusion matrices and the total correct percentage (TCP) of predictions are used to measure the prediction performance of each algorithm to identify the most realistic lithofacies classification. The TCPs for XGBoost and AdaBoost classifiers for the training subset were 98% and 100%, respectively. However, the TCPs achieved for the testing subsets were 97%, and 96%, respectively. The mismatch between the measured and predicted permeability from the XGBoost regressor was determined using root mean square error. The XGBoost model provides accurate lithofacies classification and permeability predictions of the cored data. The XGBoost model is therefore considered suitable for providing reliable predictions of lithofacies and permeability for the non-cored intervals of the same well and for non-cored wells in the studied reservoir. The workflow for lithofacies and permeability prediction was fully implemented and visualized using R open-source codes.
- North America > United States (0.70)
- Africa > Middle East > Algeria (0.68)
- Asia > Middle East > Iraq > Basra Governorate (0.47)
- Asia > Vietnam > South China Sea > Cuu Long Basin > Block 9-2 (0.99)
- Asia > Middle East > Iraq > Basra Governorate > Arabian Basin > Widyan Basin > Mesopotamian Basin > West Karoun Block > Majnoon Field > Zubair Formation (0.99)
- Asia > Middle East > Iraq > Basra Governorate > Arabian Basin > Widyan Basin > Mesopotamian Basin > West Karoun Block > Majnoon Field > Tanuma Formation (0.99)
- (10 more...)
- Reservoir Description and Dynamics > Reservoir Fluid Dynamics > Flow in porous media (1.00)
- Reservoir Description and Dynamics > Reservoir Characterization > Exploration, development, structural geology (1.00)
- Reservoir Description and Dynamics > Formation Evaluation & Management > Open hole/cased hole log analysis (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Regression (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Ensemble Learning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Performance Analysis > Accuracy (0.91)
Abstract Estimating rock facies from petrophysical logs in non-cored wells in complex carbonates represents a crucial task for improving reservoir characterization and field development. Thus, it most essential to identify the lithofacies that discriminate the reservoir intervals based on their flow and storage capacity. In this paper, an innovative procedure is adopted for lithofacies classification using data-driven machine learning in a well from the Mishrif carbonate reservoir in the giant Majnoon oil field, Southern Iraq. The Random Forest method was adopted for lithofacies classification using well logging data in a cored well to predict their distribution in other non-cored wells. Furthermore, three advanced statistical algorithms: Logistic Boosting Regression, Bagging Multivariate Adaptive Regression Spline, and Generalized Boosting Modeling were implemented and compared to the Random Forest approach to attain the most realistic lithofacies prediction. The dataset includes the measured discrete lithofacies distribution and the original log curves of caliper, gamma ray, neutron porosity, bulk density, sonic, deep and shallow resistivity, all available over the entire reservoir interval. Prior to applying the four classification algorithms, a random subsampling cross-validation was conducted on the dataset to produce training and testing subsets for modeling and prediction, respectively. After predicting the discrete lithofacies distribution, the Confusion Table and the Correct Classification Rate Index (CCI) were employed as further criteria to analyze and compare the effectiveness of the four classification algorithms. The results of this study revealed that Random Forest was more accurate in lithofacies classification than other techniques. It led to excellent matching between the observed and predicted discrete lithofacies through attaining 100% of CCI based on the training subset and 96.67 % of the CCI for the validating subset. Further validation of the resulting facies model was conducted by comparing each of the predicted discrete lithofacies with the available ranges of porosity and permeability obtained from the NMR log. We observed that rudist-dominated lithofacies correlates to rock with higher porosity and permeability. In contrast, the argillaceous lithofacies correlates to rocks with lower porosity and permeability. Additionally, these high-and low-ranges of permeability were later compared with the oil rate obtained from the PLT log data. It was identified that the high-and low-ranges of permeability correlate well to the high- and low-oil rate logs, respectively. In conclusion, the high quality estimation of lithofacies in non-cored intervals and wells is a crucial reservoir characterization task in order to obtain meaningful permeability-porosity relationships and capture realistic reservoir heterogeneity. The application of machine learning techniques drives down costs, provides for time-savings, and allows for uncertainty mitigation in lithofacies classification and prediction. The entire workflow was done through R, an open-source statistical computing language. It can easily be applied to other reservoirs to attain for them a similar improved overall reservoir characterization.
- North America > United States (1.00)
- Asia > Middle East > Iraq > Basra Governorate (1.00)
- Geology > Rock Type > Sedimentary Rock > Carbonate Rock (1.00)
- Geology > Rock Type > Sedimentary Rock > Clastic Rock > Mudrock (0.34)
- Asia > Middle East > Qatar > Arabian Gulf > Arabian Basin > Arabian Gulf Basin > Block 6 > Al Khalij Field > Mishrif Formation (0.99)
- Asia > Middle East > Iraq > Basra Governorate > Arabian Basin > Widyan Basin > Mesopotamian Basin > West Qurna Field > Yamama Formation (0.99)
- Asia > Middle East > Iraq > Basra Governorate > Arabian Basin > Widyan Basin > Mesopotamian Basin > West Qurna Field > Mishrif Formation (0.99)
- (11 more...)
Statistical Analysis of the Petrophysical Properties of the Bakken Petroleum System
Laalam, Aimen (University of North Dakota) | Ouadi, Habib (University of North Dakota) | Merzoug, Ahmed (University of North Dakota) | Chemmakh, Abderraouf (University of North Dakota) | Boualam, Aldjia (University of North Dakota) | Djezzar, Sofiane (University of North Dakota) | Mellal, Ilyas (University of North Dakota) | Djoudi, Meriem (University of Boumerdes)
Abstract Porosity and permeability represent the main parameters for an accurate petrophysical evaluation. These parameters are often evaluated either from well logs interpretation or core data. The wireline logs provide continuous measurements of physical rock properties and can be interpreted to provide porosity and permeability indirectly. Thus, it has to be inferred through relationships with core data from the same field or well or from empirically derived equations. Another approach is to model the relationship between porosity and permeability from core data which provide more accurate estimations but are expansive and cannot be acquired at every depth on every well. In addition, machine learning technics gained a lot of importance in solving similar problems. To produce a continuous permeability from a computed porosity in any well, we use statistical analysis on core data to obtain a correlation between porosity and permeability for a particular formation. This paper aims to generate permeability-porosity data-driven models for the Bakken formation, representing an unconventional reservoir within the Williston Basin in the US, using 426 core data with a wide range of porosity and permeability. Different machine learning algorithms have been developed including Linear Regression (LR), Artificial Neural Network (ANN), Random Forest Regressor (RFR), Extreme Gradient Boosting (XGBoost), Adaptive Booster Regressor (AdaBoost), and Support Vector Regression (SVR), to predict the permeability from porosity. Evaluating the obtained correlation and the machine learning algorithms was based on the R score, the Minimum Squared Error (MSE), and the Mean Absolute Error (MAE) as evaluation metrics. The developed models yielded an R score ranging from 0.61 to 0.74, with the ANN model outperforming the other algorithms resulting in the highest R score and lowest error. The models were evaluated on unseen data from other wells drilled in the same formation, and a good match of permeability was obtained. Introduction Permeability is one of the important petrophysical parameters in reservoir engineering (Zhao et al., 2022). an accurate determination is vital for hydrocarbons recovery, carbon storage, geothermal energy capacity, and well placement optimization (Byrnes, 1994). It has a strong relationship with reservoir quality evaluation and the fluid production capacity (Baas et al., 2007), which is based on reservoir characterization, the flow unit identification, and the location of the perforation intervals (Doyen, 1988; Pittman, 1992). It represents the ability of the rock to transmit fluid (Ghafoori et al., 2008). The accurate permeability detection affects the economic value of hydrocarbons accumulation and petroleum reservoir management before and during production.
- North America > United States > North Dakota (1.00)
- North America > Canada > Saskatchewan (1.00)
- North America > Canada > Manitoba (1.00)
- Asia > Middle East > Israel > Mediterranean Sea (0.24)
- Geology > Rock Type > Sedimentary Rock > Clastic Rock (0.69)
- Geology > Geological Subdiscipline > Geomechanics (0.66)
- Geology > Geological Subdiscipline > Economic Geology > Petroleum Geology (0.50)
- North America > United States > South Dakota > Williston Basin > Bakken Shale Formation (0.99)
- North America > United States > North Dakota > Williston Basin > Bakken Shale Formation > Middle Bakken Shale Formation (0.99)
- North America > United States > Montana > Williston Basin > Bakken Shale Formation (0.99)
- (2 more...)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Regression (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Ensemble Learning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Support Vector Machines (0.88)
Abstract Understanding the vertical discrete electrofacies distributions in wells is a vital step to preserve the reservoir heterogeneity. Predicting the electrofacies distribution at all wells is commonly conducted manually or with the use of some graphing approaches, but recently different machine learning techniques have been adopted to categorize electrofacies. In this paper, two supervised machine-learning techniques were implemented to model electrofacies given well logging data for a well in order to predict the distributions in all other wells (classification) in a carbonate reservoir in a giant southern Iraqi Oil Field. The available data included open-hole and CPI well logging records in addition to the routine core analysis. The well discrete electrofacies distribution for the entire reservoir thickness has been obtained in our paper [OTC-29269-MS] using the Ward Hierarchical Clustering Analysis. For electrofacies classification, two supervised machine-learning techniques, K-Nearest Neighbors (KNN) and Random Forests (RF), were adopted to model the resulting electrofacies given the CPI well logging data for a well to predict at other wells that have missing data. These two supervised learning techniques were implemented as non-linear and non-parametric classifiers, which are imperative attribute due to the non-linearity of the electrofacies properties and the geological reservoir control. The results of this research illustrated that the reservoir electrofacies can be predicted through the use of the supervised learning techniques when well logging records and core data are available. The two adopted classification algorithms were analyzed and compared based on confusion table, transition probability matrix and total percent correct (TCP) of the identified electrofacies that reveal the accuracy of the classification. RF was observed to be the optimum approach as it led to better electrofacies classification in this carbonate reservoir than the KNN. The application of supervised machine learning techniques enhanced the accuracy and reduced the time spent in electrofacies classification. The two machine learning algorithms were implemented by R software, the most powerful statistical programming language.
- North America > United States (0.47)
- Asia > Middle East > Iraq > Basra Governorate (0.29)
- Asia > Middle East > Iraq > Basra Governorate > Arabian Basin > Widyan Basin > Mesopotamian Basin > West Qurna Field > Yamama Formation (0.99)
- Asia > Middle East > Iraq > Basra Governorate > Arabian Basin > Widyan Basin > Mesopotamian Basin > West Qurna Field > Mishrif Formation (0.99)
- Asia > Middle East > Iraq > Basra Governorate > Arabian Basin > Widyan Basin > Mesopotamian Basin > Rumaila Field > Zubair Formation (0.99)
- (2 more...)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Inductive Learning (0.95)
- Information Technology > Artificial Intelligence > Machine Learning > Performance Analysis > Accuracy (0.69)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Directed Networks > Bayesian Learning (0.47)
Abstract Integrating discrete facies classification into the estimation of formation permeability is a crucial step to improve reservoir characterization and to preserve heterogeneity quantification. Therefore, it is essential to obtain the most accurate estimation of permeability in non-cored intervals in order to attain realistic reservoir characterization and modeling. In our most recent paper [OTC-30906-MS], the electrofacies classifications have been conduced for a well from a carbonate reservoir in a Giant Southern Iraqi oil field. The same predicted discrete electrofacies distribution was included in this paper along with well logging interpretations to model and predict the reservoir core permeability for all wells. The well logging interpretations that were included in permeability modelling are neutron porosity, shale volume, and water saturation as a function of depth. The regression and machine learning approaches adopted for permeability modelling are multiple linear regression (MLR), smooth generalized additive Modeling (SGAM) and Random Forest (RF) Algorithm. The classified electrofacies were considered as a discrete independent variable in the core permeability modelling to provide different model fits given each electrofacies type in order to capture the different permeability variances. The matching visualization between the observed and predicted core permeability, the computed root mean square prediction error and adjusted squared R were considered as validation and accuracy tools to compare between the three modelling approaches. Since there are too many intervals with missing core permeability measurements, the modelling was first adopted on the intervals that have permeability readings (known subset). The prediction was then conducted given the same known permeability intervals in addition to the entire dataset (full dataset). The root mean square prediction error and adjusted squared R for the Random Forest were significantly better than in both MLR and SGAM for the known subset and full dataset. It can be concluded that combining the electrofacies in one permeability model has accurate, fast and an automation procedure of prediction for other wells. The two machine learning algorithms were implemented by R software, the most powerful statistical programming language.
- North America > United States > Texas (0.47)
- Asia > Middle East > Iraq > Basra Governorate (0.28)
- Geology > Geological Subdiscipline > Petrology > Petrography (0.78)
- Geology > Rock Type > Sedimentary Rock > Clastic Rock > Mudrock (0.36)
- Asia > Middle East > Iraq > Basra Governorate > Arabian Basin > Widyan Basin > Mesopotamian Basin > West Qurna Field > Yamama Formation (0.99)
- Asia > Middle East > Iraq > Basra Governorate > Arabian Basin > Widyan Basin > Mesopotamian Basin > West Qurna Field > Mishrif Formation (0.99)
- Asia > Middle East > Iraq > Basra Governorate > Arabian Basin > Widyan Basin > Mesopotamian Basin > Rumaila Field > Zubair Formation (0.99)
- (5 more...)