The Experts below are selected from a list of 21201 Experts worldwide ranked by ideXlab platform
Scott L Montgomery - One of the best experts on this subject based on the ideXlab platform.
-
increasing reserves in a mature giant wilmington field los angeles basin part ii improving heavy oil production through advanced Reservoir Characterization and innovative thermal technologies
AAPG Bulletin, 1998Co-Authors: Scott L MontgomeryAbstract:Enhanced recovery of low-gravity oil from unconsolidated, high-porosity, high-permeability sands in the supergiant Wilmington field began in the early 1960s. Despite nearly four decades of production, postprimary recoveries have been generally low due to Reservoir heterogeneity and operational problems. In particular, steamflooding has yielded poor results because of elevated steam:oil ratios, early steam breakthrough, and consequent premature equipment failure. A multidiscipline effort to address these problems and improve recovery is underway as part of the U.S. Department of Energy Class III (slope and basin clastic Reservoir) Oil Recovery Field Demonstration initiative. In the fault block IIA portion of Wilmington field, this effort has focused on several main objectives. Those objectives discussed in this paper include (1) three-dimensional geologic modeling to rigorously define important relationships; (2) rock typing and rock-log modeling to improve Reservoir Characterization; (3) testing the feasibility of using horizontal wells in steamflood operations at Wilmington; and (4) employing a novel, low-cost completion technique applicable to unconsolidated formations. To date, significant levels of success have been achieved with regard to all these objectives. When complete, the project at Wilmington field should have wide-ranging application to similar Reservoirs throughout southern California and elsewhere.
-
increasing reserves in a mature giant wilmington field los angeles basin part 1 Reservoir Characterization to identify bypassed oil
AAPG Bulletin, 1998Co-Authors: Scott L MontgomeryAbstract:With estimated reserves of over 2.8 billion bbl oil, the supergiant Wilmington field is the largest productive area in the Los Angeles basin, one of the worlds most prolific petroleum provinces. Similar to most other fields in the basin, Wilmington produces from thick sequences of upper Miocene-Pliocene slope and basin-floor turbidites ranging from well indurated to unconsolidated in character. Due to a range of factors, enhanced recovery in these Reservoirs has been incomplete or inefficient, with the result that a substantial remaining resource exists. To help devise improved methods for exploiting this resource, the U.S. Department of Energy has included portions of Wilmington field in its "Class 3 [slope and basin clastic Reservoirs] Oil Recovery Field Demonstration Program." At present, two projects are underway: one aimed at identifying bypassed pay, and the other project aimed at improving tertiary recovery operations. Both projects have employed advanced Reservoir Characterization techniques and have demonstrated considerable success. Results of this work should have wide application to slope and basin clastic Reservoirs elsewhere. Part 1 of the following two-part paper presents a summary of work completed thus far.
Abdulazeez Abdulraheem - One of the best experts on this subject based on the ideXlab platform.
-
Hybrid intelligent systems in petroleum Reservoir Characterization and modeling: the journey so far and the challenges ahead
Journal of Petroleum Exploration and Production Technology, 2017Co-Authors: Fatai Anifowose, Jane Labadin, Abdulazeez AbdulraheemAbstract:Computational intelligence (CI) techniques have positively impacted the petroleum Reservoir Characterization and modeling landscape. However, studies have showed that each CI technique has its strengths and weaknesses. Some of the techniques have the ability to handle datasets of high dimensionality and fast in execution, while others are limited in their ability to handle uncertainties, difficult to learn, and could not deal with datasets of high or low dimensionality. The “no free lunch” theorem also gives credence to this problem as it postulates that no technique or method can be applicable to all problems in all situations. A technique that worked well on a problem may not perform well in another problem domain just as a technique that was written off on one problem may be promising with another. There was the need for robust techniques that will make the best use of the strengths to overcome the weaknesses while producing the best results. The machine learning concepts of hybrid intelligent system (HIS) have been proposed to partly overcome this problem. In this review paper, the impact of HIS on the petroleum Reservoir Characterization process is enumerated, analyzed, and extensively discussed. It was concluded that HIS has huge potentials in the improvement of petroleum Reservoir property predictions resulting in improved exploration, more efficient exploitation, increased production, and more effective management of energy resources. Lastly, a number of yet-to-be-explored hybrid possibilities were recommended.
-
ensemble machine learning an untapped modeling paradigm for petroleum Reservoir Characterization
Journal of Petroleum Science and Engineering, 2017Co-Authors: Fatai Anifowose, Jane Labadin, Abdulazeez AbdulraheemAbstract:Abstract The successful applications of the conventional Computational Intelligence (CI) techniques and Hybrid Intelligent Systems (HIS) in petroleum Reservoir Characterization have been reported. However, these techniques are limited in their capability to handle a single hypothesis of a problem at a time. The major objective of the Reservoir Characterization process is to produce models that are robust enough to help improve the accuracy of the predictions of Reservoir properties for use in full-field and large-scale simulation models. Research in CI continues to evolve new techniques and paradigms to meet this noble objective. It has been shown that there are uncertainties in the Reservoir Characterization process as well as the optimal choice of CI/HIS models parameters. The main challenge is to develop models that are capable of handling multiple hypotheses to reduce the uncertainties thereby ensuring optimal solutions. The ensemble machine learning paradigm has been established to tackle this challenge. This new machine learning technology has not been adequately explored in handling some of the petroleum engineering challenges. This paper rigorously reviews the concept of ensemble learning paradigm, presents successful applications outside petroleum engineering and the geosciences, discusses a few successful attempts in petroleum engineering and the geosciences, and concludes with some recommendations for the much-needed future applications.
-
improving the prediction of petroleum Reservoir Characterization with a stacked generalization ensemble model of support vector machines
Applied Soft Computing, 2015Co-Authors: Fatai Anifowose, Jane Labadin, Abdulazeez AbdulraheemAbstract:Despite successful applications of ensembles, the petroleum industry has not benefited enough.SVM is promising but its performance depends mostly on the regularization parameter.We propose an SVM ensemble with diverse opinions on the regularization parameter.The proposed model outperformed Random Forest but competitive with SVM Bagging.There is great potential for ensemble models in petroleum Reservoir Characterization. The ensemble learning paradigm has proved to be relevant to solving most challenging industrial problems. Despite its successful application especially in the Bioinformatics, the petroleum industry has not benefited enough from the promises of this machine learning technology. The petroleum industry, with its persistent quest for high-performance predictive models, is in great need of this new learning methodology. A marginal improvement in the prediction indices of petroleum Reservoir properties could have huge positive impact on the success of exploration, drilling and the overall Reservoir management portfolio. Support vector machines (SVM) is one of the promising machine learning tools that have performed excellently well in most prediction problems. However, its performance is a function of the prudent choice of its tuning parameters most especially the regularization parameter, C. Reports have shown that this parameter has significant impact on the performance of SVM. Understandably, no specific value has been recommended for it. This paper proposes a stacked generalization ensemble model of SVM that incorporates different expert opinions on the optimal values of this parameter in the prediction of porosity and permeability of petroleum Reservoirs using datasets from diverse geological formations. The performance of the proposed SVM ensemble was compared to that of conventional SVM technique, another SVM implemented with the bagging method, and Random Forest technique. The results showed that the proposed ensemble model, in most cases, outperformed the others with the highest correlation coefficient, and the lowest mean and absolute errors. The study indicated that there is a great potential for ensemble learning in petroleum Reservoir Characterization to improve the accuracy of Reservoir properties predictions for more successful explorations and increased production of petroleum resources. The results also confirmed that ensemble models perform better than the conventional SVM implementation.
-
non linear feature selection based hybrid computational intelligence models for improved natural gas Reservoir Characterization
Journal of Natural Gas Science and Engineering, 2014Co-Authors: Fatai Anifowose, Jane Labadin, Abdulazeez AbdulraheemAbstract:Abstract With the recent state-of-the-art sensor-based data acquisition tools in the oil and gas industry, datasets sometimes come in very high dimensions. There is the need to extract the most relevant features out of these datasets to keep predictive models simple, accurate and free of pollution with irrelevant information. Multi-variate regression methods and evolutionary algorithms have been used to achieve this feat. However, the former could not handle the non-linearity in most problems that involve natural phenomena such as oil and gas Reservoir Characterization. The latter have been shown to introduce computational and time complexities, and are sometimes not very efficient. Accurate predictions of oil and gas Reservoir properties are important for more efficient exploration and production of fossil energy resources. This paper proposes three non-linear feature selection based hybrid models in the prediction of porosity and permeability of two geographically and lithologically differentiated heterogeneous Reservoirs. The hybrid models utilized the non-linear feature selection capabilities of Functional Networks (FN), Decision Trees (DT) and Fuzzy Ranking (FR) algorithms with the excellent functional approximation capability of Support Vector Machines (SVM). The results of the proposed models were then compared with a previously implemented FN-based Type-2 Fuzzy Logic hybrid model and the respective standalone components of the hybrid models. The comparative results provided more understanding of the architecture of these feature selection algorithms and further confirmed the importance of the feature selection process in oil and gas Reservoir Characterization. In the overall, the FN–SVM hybrid model showed superior performance in terms of correlation coefficient, root mean square error and execution time.
Fatai Anifowose - One of the best experts on this subject based on the ideXlab platform.
-
Hybrid intelligent systems in petroleum Reservoir Characterization and modeling: the journey so far and the challenges ahead
Journal of Petroleum Exploration and Production Technology, 2017Co-Authors: Fatai Anifowose, Jane Labadin, Abdulazeez AbdulraheemAbstract:Computational intelligence (CI) techniques have positively impacted the petroleum Reservoir Characterization and modeling landscape. However, studies have showed that each CI technique has its strengths and weaknesses. Some of the techniques have the ability to handle datasets of high dimensionality and fast in execution, while others are limited in their ability to handle uncertainties, difficult to learn, and could not deal with datasets of high or low dimensionality. The “no free lunch” theorem also gives credence to this problem as it postulates that no technique or method can be applicable to all problems in all situations. A technique that worked well on a problem may not perform well in another problem domain just as a technique that was written off on one problem may be promising with another. There was the need for robust techniques that will make the best use of the strengths to overcome the weaknesses while producing the best results. The machine learning concepts of hybrid intelligent system (HIS) have been proposed to partly overcome this problem. In this review paper, the impact of HIS on the petroleum Reservoir Characterization process is enumerated, analyzed, and extensively discussed. It was concluded that HIS has huge potentials in the improvement of petroleum Reservoir property predictions resulting in improved exploration, more efficient exploitation, increased production, and more effective management of energy resources. Lastly, a number of yet-to-be-explored hybrid possibilities were recommended.
-
ensemble machine learning an untapped modeling paradigm for petroleum Reservoir Characterization
Journal of Petroleum Science and Engineering, 2017Co-Authors: Fatai Anifowose, Jane Labadin, Abdulazeez AbdulraheemAbstract:Abstract The successful applications of the conventional Computational Intelligence (CI) techniques and Hybrid Intelligent Systems (HIS) in petroleum Reservoir Characterization have been reported. However, these techniques are limited in their capability to handle a single hypothesis of a problem at a time. The major objective of the Reservoir Characterization process is to produce models that are robust enough to help improve the accuracy of the predictions of Reservoir properties for use in full-field and large-scale simulation models. Research in CI continues to evolve new techniques and paradigms to meet this noble objective. It has been shown that there are uncertainties in the Reservoir Characterization process as well as the optimal choice of CI/HIS models parameters. The main challenge is to develop models that are capable of handling multiple hypotheses to reduce the uncertainties thereby ensuring optimal solutions. The ensemble machine learning paradigm has been established to tackle this challenge. This new machine learning technology has not been adequately explored in handling some of the petroleum engineering challenges. This paper rigorously reviews the concept of ensemble learning paradigm, presents successful applications outside petroleum engineering and the geosciences, discusses a few successful attempts in petroleum engineering and the geosciences, and concludes with some recommendations for the much-needed future applications.
-
improving the prediction of petroleum Reservoir Characterization with a stacked generalization ensemble model of support vector machines
Applied Soft Computing, 2015Co-Authors: Fatai Anifowose, Jane Labadin, Abdulazeez AbdulraheemAbstract:Despite successful applications of ensembles, the petroleum industry has not benefited enough.SVM is promising but its performance depends mostly on the regularization parameter.We propose an SVM ensemble with diverse opinions on the regularization parameter.The proposed model outperformed Random Forest but competitive with SVM Bagging.There is great potential for ensemble models in petroleum Reservoir Characterization. The ensemble learning paradigm has proved to be relevant to solving most challenging industrial problems. Despite its successful application especially in the Bioinformatics, the petroleum industry has not benefited enough from the promises of this machine learning technology. The petroleum industry, with its persistent quest for high-performance predictive models, is in great need of this new learning methodology. A marginal improvement in the prediction indices of petroleum Reservoir properties could have huge positive impact on the success of exploration, drilling and the overall Reservoir management portfolio. Support vector machines (SVM) is one of the promising machine learning tools that have performed excellently well in most prediction problems. However, its performance is a function of the prudent choice of its tuning parameters most especially the regularization parameter, C. Reports have shown that this parameter has significant impact on the performance of SVM. Understandably, no specific value has been recommended for it. This paper proposes a stacked generalization ensemble model of SVM that incorporates different expert opinions on the optimal values of this parameter in the prediction of porosity and permeability of petroleum Reservoirs using datasets from diverse geological formations. The performance of the proposed SVM ensemble was compared to that of conventional SVM technique, another SVM implemented with the bagging method, and Random Forest technique. The results showed that the proposed ensemble model, in most cases, outperformed the others with the highest correlation coefficient, and the lowest mean and absolute errors. The study indicated that there is a great potential for ensemble learning in petroleum Reservoir Characterization to improve the accuracy of Reservoir properties predictions for more successful explorations and increased production of petroleum resources. The results also confirmed that ensemble models perform better than the conventional SVM implementation.
-
non linear feature selection based hybrid computational intelligence models for improved natural gas Reservoir Characterization
Journal of Natural Gas Science and Engineering, 2014Co-Authors: Fatai Anifowose, Jane Labadin, Abdulazeez AbdulraheemAbstract:Abstract With the recent state-of-the-art sensor-based data acquisition tools in the oil and gas industry, datasets sometimes come in very high dimensions. There is the need to extract the most relevant features out of these datasets to keep predictive models simple, accurate and free of pollution with irrelevant information. Multi-variate regression methods and evolutionary algorithms have been used to achieve this feat. However, the former could not handle the non-linearity in most problems that involve natural phenomena such as oil and gas Reservoir Characterization. The latter have been shown to introduce computational and time complexities, and are sometimes not very efficient. Accurate predictions of oil and gas Reservoir properties are important for more efficient exploration and production of fossil energy resources. This paper proposes three non-linear feature selection based hybrid models in the prediction of porosity and permeability of two geographically and lithologically differentiated heterogeneous Reservoirs. The hybrid models utilized the non-linear feature selection capabilities of Functional Networks (FN), Decision Trees (DT) and Fuzzy Ranking (FR) algorithms with the excellent functional approximation capability of Support Vector Machines (SVM). The results of the proposed models were then compared with a previously implemented FN-based Type-2 Fuzzy Logic hybrid model and the respective standalone components of the hybrid models. The comparative results provided more understanding of the architecture of these feature selection algorithms and further confirmed the importance of the feature selection process in oil and gas Reservoir Characterization. In the overall, the FN–SVM hybrid model showed superior performance in terms of correlation coefficient, root mean square error and execution time.
Tapan Mukerji - One of the best experts on this subject based on the ideXlab platform.
-
Combining seismic Reservoir Characterization workflows with basin modeling in the deepwater Gulf of Mexico Mississippi Canyon area
AAPG Bulletin, 2018Co-Authors: Wisam H. Alkawai, Tapan Mukerji, Allegra Hosford Scheirer, Stephan A. GrahamAbstract:In this study, we explore the value added by application of basin modeling to seismic Reservoir Characterization in a structurally complex area. We focus on the Thunder Horse minibasin in the Gulf of Mexico. First, we build a two-dimensional basin model along the strike direction of the main structure in the area to investigate differences in pressure and thermal histories. The results suggest differences in both histories across the study area, and these differences can be reasonably assessed by basin modeling even with a single well calibration. We combine basin modeling results with rock physics models to build a training data set of seismic impedance derived lithofacies. The training data set thus captures spatial trends in the desired property beyond available well data. In addition, we demonstrate how to improve the seismic inversion results by integrating the basin modeling insights with limited well data. Our new workflow combining basin modeling output with rock physics and impedance-based lithofacies prediction significantly improves the predicted spatial distribution of Reservoir lithofacies in the scenarios of spatially limited well control.
-
adaptive spatial resampling as a markov chain monte carlo method for stochastic seismic Reservoir Characterization
Seg Technical Program Expanded Abstracts, 2012Co-Authors: Cheolkyun Jeong, Tapan Mukerji, Gregoire MariethozAbstract:Summary Seismic Reservoir Characterization aims to transform obtained seismic signatures into Reservoir properties such as lithofacies and pore fluids. We propose a Markov chain Monte Carlo (McMC) workflow consistent with geology, well-logs, seismic data and rock-physics information. The workflow uses a multiple-point geostatistical method for generating realizations from the prior distribution and Adaptive Spatial Resampling (ASR) for sampling from the posterior distribution conditioned to seismic data. Sampling is a general approach for assessing important uncertainties. However, rejection sampling requires a large number of evaluations of forward model, and is not efficient for Reservoir modeling. Metropolis sampling is able to perform a reasonably equivalent sampling by forming a Markov chain. The ASR algorithm perturbs realizations of a spatially dependent variable while preserving its spatial structure. The method is used as a transition kernel to produce a Markov chain of geostatistical realizations. These realizations are converted to predicted seismic data by forward modeling, to compute the likelihood. Depending on the acceptation/rejection criterion in the Markov process, it is possible to obtain a chain of realizations aimed either at characterizing the posterior distribution with Metropolis sampling or at calibrating a single realization until an optimum is reached. Thus the algorithm can be tuned to work either as an optimizer or as a sampler. The validity and applicability of the proposed method and sensitivity of different parameters is explored using synthetic seismic data.
-
stochastic Reservoir Characterization using prestack seismic data
Geophysics, 2004Co-Authors: Jo Eidsvik, Tapan Mukerji, Per Avseth, Henning Omre, Gary MavkoAbstract:Reservoir Characterization must be based on information from various sources. Well observations, seismic reflection times, and seismic amplitude versus offset (AVO) attributes are integrated in this study to predict the distribution of the Reservoir variables, i.e., facies and fluid filling. The prediction problem is cast in a Bayesian setting. The a priori model includes spatial coupling through Markov random field assumptions and intervariable dependencies through nonlinear relations based on rock physics theory, including Gassmann's relation. The likelihood model relating observations to Reservoir variables (including lithology facies and pore fluids) is based on approximations to Zoeppritz equations. The model assumptions are summarized in a Bayesian network illustrating the dependencies between the Reservoir variables. The posterior model for the Reservoir variables conditioned on the available observations is defined by the a priori and likelihood models. This posterior model is not analytically tra...
-
statistical rock physics combining rock physics information theory and geostatistics to reduce uncertainty in seismic Reservoir Characterization
Geophysics, 2001Co-Authors: Tapan Mukerji, Per Avseth, Gary Mavko, Isao Takahashi, Ezequiel F GonzalezAbstract:“Any physical theory is a kind of guesswork. There are good guesses and bad guesses. The language of probability allows us to speak quantitatively about some situation which may be highly variable, but which does have some consistent average behavior…. Our most precise description of nature must be in terms of probabilities.” —Richard Feynman This paper presents snapshots of current and emerging trends in applied statistical rock physics for Reservoir Characterization. By integrating fundamental concepts and models of rock physics, statistical pattern recognition, and information theory with seismic inversion and geostatistics, we can quantify and reduce uncertainties in Reservoir management. Rock physics allows us to link seismic response and Reservoir properties and to extend the available data to generate training data for the classification system. Seismic imaging brings indirect, but nevertheless spatially exhaustive, lateral and vertical information about Reservoir properties that are not available from pinpoint well data. Classification and estimation methods based on computational statistical techniques such as nonparametric Bayesian classification, bootstrap, and neural networks help quantitatively measure interpretation uncertainty and the mis-classification risk at each spatial location. Geostatistical stochastic simulations add spatial correlation and small-scale variability which is hard to identify from seismic only because of the limits of resolution. Combining deterministic physical models with statistical techniques leads to new methods for interpretation and estimation of Reservoir rock properties from seismic data. These formulations identify the most likely interpretation, the uncertainty of the interpretation, and guide quantitative decision analysis. Subsurface heterogeneity delineation is a key factor in reliable Reservoir Characterization. These heterogeneities occur at various scales and can include variations in lithology, pore fluids, clay content, porosity, pressure, and temperature. Some methods used in seismic Reservoir Characterization are purely statistical. Others are deterministic, based on physical models (theoretical, laboratory). Each group of techniques can have some …
Jane Labadin - One of the best experts on this subject based on the ideXlab platform.
-
Hybrid intelligent systems in petroleum Reservoir Characterization and modeling: the journey so far and the challenges ahead
Journal of Petroleum Exploration and Production Technology, 2017Co-Authors: Fatai Anifowose, Jane Labadin, Abdulazeez AbdulraheemAbstract:Computational intelligence (CI) techniques have positively impacted the petroleum Reservoir Characterization and modeling landscape. However, studies have showed that each CI technique has its strengths and weaknesses. Some of the techniques have the ability to handle datasets of high dimensionality and fast in execution, while others are limited in their ability to handle uncertainties, difficult to learn, and could not deal with datasets of high or low dimensionality. The “no free lunch” theorem also gives credence to this problem as it postulates that no technique or method can be applicable to all problems in all situations. A technique that worked well on a problem may not perform well in another problem domain just as a technique that was written off on one problem may be promising with another. There was the need for robust techniques that will make the best use of the strengths to overcome the weaknesses while producing the best results. The machine learning concepts of hybrid intelligent system (HIS) have been proposed to partly overcome this problem. In this review paper, the impact of HIS on the petroleum Reservoir Characterization process is enumerated, analyzed, and extensively discussed. It was concluded that HIS has huge potentials in the improvement of petroleum Reservoir property predictions resulting in improved exploration, more efficient exploitation, increased production, and more effective management of energy resources. Lastly, a number of yet-to-be-explored hybrid possibilities were recommended.
-
ensemble machine learning an untapped modeling paradigm for petroleum Reservoir Characterization
Journal of Petroleum Science and Engineering, 2017Co-Authors: Fatai Anifowose, Jane Labadin, Abdulazeez AbdulraheemAbstract:Abstract The successful applications of the conventional Computational Intelligence (CI) techniques and Hybrid Intelligent Systems (HIS) in petroleum Reservoir Characterization have been reported. However, these techniques are limited in their capability to handle a single hypothesis of a problem at a time. The major objective of the Reservoir Characterization process is to produce models that are robust enough to help improve the accuracy of the predictions of Reservoir properties for use in full-field and large-scale simulation models. Research in CI continues to evolve new techniques and paradigms to meet this noble objective. It has been shown that there are uncertainties in the Reservoir Characterization process as well as the optimal choice of CI/HIS models parameters. The main challenge is to develop models that are capable of handling multiple hypotheses to reduce the uncertainties thereby ensuring optimal solutions. The ensemble machine learning paradigm has been established to tackle this challenge. This new machine learning technology has not been adequately explored in handling some of the petroleum engineering challenges. This paper rigorously reviews the concept of ensemble learning paradigm, presents successful applications outside petroleum engineering and the geosciences, discusses a few successful attempts in petroleum engineering and the geosciences, and concludes with some recommendations for the much-needed future applications.
-
improving the prediction of petroleum Reservoir Characterization with a stacked generalization ensemble model of support vector machines
Applied Soft Computing, 2015Co-Authors: Fatai Anifowose, Jane Labadin, Abdulazeez AbdulraheemAbstract:Despite successful applications of ensembles, the petroleum industry has not benefited enough.SVM is promising but its performance depends mostly on the regularization parameter.We propose an SVM ensemble with diverse opinions on the regularization parameter.The proposed model outperformed Random Forest but competitive with SVM Bagging.There is great potential for ensemble models in petroleum Reservoir Characterization. The ensemble learning paradigm has proved to be relevant to solving most challenging industrial problems. Despite its successful application especially in the Bioinformatics, the petroleum industry has not benefited enough from the promises of this machine learning technology. The petroleum industry, with its persistent quest for high-performance predictive models, is in great need of this new learning methodology. A marginal improvement in the prediction indices of petroleum Reservoir properties could have huge positive impact on the success of exploration, drilling and the overall Reservoir management portfolio. Support vector machines (SVM) is one of the promising machine learning tools that have performed excellently well in most prediction problems. However, its performance is a function of the prudent choice of its tuning parameters most especially the regularization parameter, C. Reports have shown that this parameter has significant impact on the performance of SVM. Understandably, no specific value has been recommended for it. This paper proposes a stacked generalization ensemble model of SVM that incorporates different expert opinions on the optimal values of this parameter in the prediction of porosity and permeability of petroleum Reservoirs using datasets from diverse geological formations. The performance of the proposed SVM ensemble was compared to that of conventional SVM technique, another SVM implemented with the bagging method, and Random Forest technique. The results showed that the proposed ensemble model, in most cases, outperformed the others with the highest correlation coefficient, and the lowest mean and absolute errors. The study indicated that there is a great potential for ensemble learning in petroleum Reservoir Characterization to improve the accuracy of Reservoir properties predictions for more successful explorations and increased production of petroleum resources. The results also confirmed that ensemble models perform better than the conventional SVM implementation.
-
non linear feature selection based hybrid computational intelligence models for improved natural gas Reservoir Characterization
Journal of Natural Gas Science and Engineering, 2014Co-Authors: Fatai Anifowose, Jane Labadin, Abdulazeez AbdulraheemAbstract:Abstract With the recent state-of-the-art sensor-based data acquisition tools in the oil and gas industry, datasets sometimes come in very high dimensions. There is the need to extract the most relevant features out of these datasets to keep predictive models simple, accurate and free of pollution with irrelevant information. Multi-variate regression methods and evolutionary algorithms have been used to achieve this feat. However, the former could not handle the non-linearity in most problems that involve natural phenomena such as oil and gas Reservoir Characterization. The latter have been shown to introduce computational and time complexities, and are sometimes not very efficient. Accurate predictions of oil and gas Reservoir properties are important for more efficient exploration and production of fossil energy resources. This paper proposes three non-linear feature selection based hybrid models in the prediction of porosity and permeability of two geographically and lithologically differentiated heterogeneous Reservoirs. The hybrid models utilized the non-linear feature selection capabilities of Functional Networks (FN), Decision Trees (DT) and Fuzzy Ranking (FR) algorithms with the excellent functional approximation capability of Support Vector Machines (SVM). The results of the proposed models were then compared with a previously implemented FN-based Type-2 Fuzzy Logic hybrid model and the respective standalone components of the hybrid models. The comparative results provided more understanding of the architecture of these feature selection algorithms and further confirmed the importance of the feature selection process in oil and gas Reservoir Characterization. In the overall, the FN–SVM hybrid model showed superior performance in terms of correlation coefficient, root mean square error and execution time.