Watheq J. Al-Mudhafar

Geostatistical lithofacies modeling of the upper sandstone member/Zubair formation in south Rumaila oil field, Iraq

Geological facies modeling is a crucial problem for reservoir characterization as it affects the reservoir heterogeneities and fluid flow performance prediction. The main purpose of this research is to adopt a stochastic simulation to construct 3D lithofacies models of the tidal/estuarine depositional environment of the upper sandstone member in south Rumaila oil field, located in Iraq. Based on core measurements, the upper sandstone member has three main lithofacies: sand, shaly sand, and shale. Literature review indicates that the formation is encompassed of mainly sandstone with some inter-bedded shale zones. To reconstruct the 3D lithofacies model, the sequential indicator simulation (SISIM) was adopted to build the categorical image, pixel by pixel, considering the nonparametric condition distribution. Specifically, SISIM depends on the variogram to address and model the variation between any two spatial points from the available data. Therefore, 12 different variograms were constructed given the three lithofacies in four different azimuth directions: 0°, 45°, 90°, and 135°.The resulting lithofacies models in the four selected azimuth directions have shown frequent tidal lithofacies channeling and indicate an approximate matching with the original description of the formation depositional environment of the tidal-dominated and sand-rich environment. The generated lithofacies model in 135° direction has sand channels prevailing towards the southeast shoreline of the reservoir. The created lithofacies model also preserves the reservoir complexity and heterogeneity because it was created using a high-resolution gridding system with approximately two million grids. Additionally, the resulting tidal lithofacies model ensures reservoir heterogeneity as the petrophysical properties are then distributed given each lithofacies with distinct indicator variograms.

Integrating Component Analysis & Classification Techniques for Comparative Prediction of Continuous & Discrete Lithofacies Distributions

Precisely predicting rock facies leads to adequate reservoir characterization by improving the porosity-permeability relationships to estimate the properties in non-cored intervals. It also helps to accurately identify the spatial facies distribution to perform an accurate reservoir model for optimal future reservoir performance. In this paper, comparative conditional posterior probabilities of continuous well facies distribution has been estimated through Linear Discriminate Analysis (LDA) and Kernel Support Vector Machine (KSVM) given the well log interpretations in a well within sandstone formation in South Rumaila Oil Field, located in Iraq. The explanatory variables are depth, neutron porosity, water saturation, shale volume. The multinomial response factor is the vertical discrete Lithofacies sequence that only encompasses of sand, shaly sand, and shale. The Lithofacies were modeled given the well logs data through LDA and KSVM and comparisons were done between the measured and predicted Lithofacies distribution in order to determine the best classification method to be considered for Lithofacies prediction at other wells in the reservoir.The LDA was chosen to estimate the maximum likelihood and minimize the standard error for the relationships between lithofacies and well logs data. The Linear discriminate Analysis seeks a linear transformation (discriminate function) of both the independent and dependent variables in order to produce a new set of transformed values that provides a more accurate discrimination concerning dimensionality reduction. Beta distribution of facies has been considered as prior knowledge and the resulted predicted probability (posterior) distribution has been estimated from LDA based on Bayes theorem that represents the relationship between predicted probability (posterior) with the conditional probability and the prior knowledge. The linear discriminant analysis has been accomplished considering the cross-validation in addition to splitting the data into train and test process. Through assessing the LDA models, the cross-validation was adopted as an optimal solution to estimate the continuous lithofacies distribution because the total true correct summation is more valuable than the splitting data method. Then, the KSVM has been adopted to estimate the continuous predicted probability Distribution of Lithofacies. KSVM is a supervised statistical learning algorithm that recognizes the discrete classes for the given data based on maximizing the margin around the separating hyperplane and the decision function is fully specified by a subset of the supporting vectors. The posterior distribution has been validated using the true and predicted facies counts matrix that estimated by KSVM. In comparison between the LDA and KSVM, it was prominent that KSVM is better than LDA because it has more total true correct summation than LDA. Also, nonlinear separations of components is handled well by using KSVM. In addition and after depicting the vertical well sand, shale, and shaly sand posterior distribution from both LDA and KSVM, it was shown that KSVM prediction is more compatible between the sand posterior values with the high records of neutron porosity along with low intervals of shale volume. Consequently, the KSVM was considered for Lithofacies prediction in the other wells in the reservoir to be a solid basis for the geospatial modeling.

Integrating kernel support vector machines for efficient rock facies classification in the main pay of Zubair formation in South Rumaila oil field, Iraq

Precisely prediction of rock facies leads to adequate reservoir characterization by improving the porosity-permeability relationships and accurately identifying the spatial facies distribution. In this paper, the discrete and conditional posterior probability distributions of well lithofacies were modeled and predicted through the Kernel Support Vector Machines (KSVM) as a function of well log interpretations in a well in the Upper Sandstone Member of Zubair formation in South Rumaila Oil Field, located in Iraq. The log data include neutron porosity, water saturation, and shale volume. The multinomial response factor is the measured vertical Lithofacies sequence that has mainly sand, shale, and shaly sand. KSVM is a supervised statistical learning algorithm that recognizes the discrete classes for the given data based on maximizing the margin around the separating hyperplane and the decision function is fully specified by a subset of the Support vectors. The predicted lithofacies were validated by computing the total correct percent of predicted facies counts matrix, estimated by KSVM. The nonlinear separations of components handled by KSVM led to obtaining high level of accuracy of lithofacies prediction and attained 99.55% of the total correct percent. After depicting the vertical sand, shale, and shaly sand posterior distribution, it was shown that KSVM prediction has compatible between the sand posterior values with the high records of neutron porosity and low intervals of shale volume. Consequently, the KSVM can be considered for Lithofacies prediction in the other wells in the reservoir to provide a solid basis for the geospatial modeling.

Integrating well log interpretations for lithofacies classification and permeability modeling through advanced machine learning algorithms

In this paper, an integrated procedure was adopted to obtain accurate lithofacies classification to be incorporated with well log interpretations for a precise core permeability modeling. Probabilistic neural networks (PNNs) were employed to model lithofacies sequences as a function of well logging data in order to predict discrete lithofacies distribution at missing intervals. Then, the generalized boosted regression model (GBM) was used as to build a nonlinear relationship between core permeability, well logging data, and lithofacies. The well log interpretations that were considered for lithofacies classification and permeability modeling are neutron porosity, shale volume, and water saturation as a function of depth; however, the measured discrete lithofacies types are sand, shaly sand, and shale. Accurate lithofacies classification was achieved by the PNN as the total percent correct of the predicted discrete lithofacies was 95.81%. In GBM results, root-mean-square prediction error and adjusted R-square have incredible positive values, as there was an excellent matching between the measured and predicted core permeability. Additionally, the GBM model led to overcome the multicollinearity that was available between one pair of the predictors. The efficiency of boosted regression was demonstrated by the prediction matching of core permeability in comparison with the conventional multiple linear regression (MLR). GBM led to much more accurate permeability prediction than the MLR.

Bayesian and LASSO Regressions for Comparative Permeability Modeling of Sandstone Reservoirs

In this research, Bayesian model averaging (BMA) and least absolute shrinkage and selection operator regression (LASSO) algorithms were adopted for the core permeability modeling as a function of well log and core measurements. More specifically, the core permeability (dependent factor) was modeled given the well log and core data (independent variables) and then predicted in non-cored intervals of a well in a sandstone formation. The BMA is a stochastic linear modeling and a Bayesian parameter selection. Among 50 linear models generated as a function of the independent variables and depicted in Occam’s window, the best model of the highest posterior probability is determined. The best model has the optimal subset parameters that most influences the response factor. The core permeability modeling was again conducted using the LASSO algorithm, which adopts a completely different way of modeling and subset selection by using the penalized least-squared equation. Both BMA and LASSO resulted in a very accurate prediction of the core permeability by achieving perfect measured and calculated permeability matching. Matches for the two algorithms were quantified by computing the adjusted R-squared and root-mean-squared prediction error. In addition, results of the BMA and LASSO were compared to the conventional multiple linear regression (LM). The LASSO algorithm led to an accurate matching similar to LM, but slightly better than BMA. Therefore, both BMA and LASSO represent integrated procedures for accurate permeability estimation similar to conventional regression analysis.

Hybrid Process of Gas and Downhole Water Sink-Assisted Gravity Drainage (G&DWS-AGD) to Enhance Oil Recovery in Reservoirs with Water Coning

The Gas-Assisted Gravity Drainage (GAGD) process has been suggested to enhance oil recovery by placing vertical injectors for CO2 at the top of the reservoir with a series of horizontal producers located at the bottom. The injected gas accumulates to form a gas cap while oil and water drain down to the bottom due to their heavier densities. The GAGD process has limitations with regards to the high levels of water cut and high tendency of water coning. This paper delivers an integration of downhole water sink (DWS) and the GAGD processes to overcome these limitations and further enhance oil recovery. The hybrid process, of Gas and Downhole Water Sink-Assisted Gravity Drainage (G&DWS-AGD) was developed and verified to minimize water cut in oil production wells from reservoirs with edge and/or bottom water drive and strong water coning tendencies. In the process, two 7 inch production casings are installed bi-laterally and completed using two 2-3/8 inch horizontal tubings: one above the oil-water contact (OWC) for oil production and another one underneath OWC for water sink drainage. The two completions are hydraulically isolated inside the well by a packer. The bottom (water sink) completion is produced with a submersible pump that drains the formation water from around the well and prevents the water from breaking through the oil column and getting into the horizontal oil-producing perforations. The G&DWS-AGD was evaluated for improvement of oil recovery from the upper sandstone member/South Rumaila Oilfield, located in Iraq. (The Rumaila field has an infinite active aquifer with very strong edge water drive.) The evaluation study involved a series of simulation runs to determine the best design of the combined processes. Operational variants of the process included oil and water production only, oil and water production with constant, progressive (by 50psi) and reduced (by 200 psi) gas injection pressure. In the G&DWS-AGD, the water sink operation not only eliminated (or reduced) water cut and coning tendency, but it also significantly reduced reservoir pressure, resulting in improved gas injectivity and increased oil recovery. More specifically, the 10-year production forecast showed that oil production increased by 55.1 million barrels larger than the GAGD process alone and water cut decreased from 98% to less than 5% in all the horizontal oil producers. The advantage of G&DWS-AGD process comes from its potential effectiveness to improve oil recovery while reducing water coning, water cut, and improving gas injectivity. This leads to more economic implementation, especially with respect to the operational surface facilities. Introduction The Gas-Assisted Gravity Drainage (GAGD) process has been suggested for improved oil recovery in secondary and tertiary processes for both immiscible and miscible injection modes. The GAGD involved injecting gas through vertical wells in a gravity-stable mode to build a gas cap resulting in oil drainage downwards to the bottom of reservoir comprising several horizontal producers (Rao et al. , 2004). The mechanisms of fluid segregation and gravity oil drainage give better sweep efficiency and higher oil recovery.