Prediction of permeability of highly heterogeneous hydrocarbon reservoir from conventional petrophysical logs using optimized data-driven algorithms
Abstract Permeability is an important parameter in the petrophysical study of a reservoir and serves as a key tool in the development of an oilfield. This is while its prediction, especially in carbonate reservoirs with their relatively lower levels of permeability compared to sandstone reservoirs,...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-12-01
|
| Series: | Journal of Petroleum Exploration and Production Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s13202-022-01593-z |
| _version_ | 1797865482480517120 |
|---|---|
| author | Amirhossein Sheykhinasab Amir Ali Mohseni Arash Barahooie Bahari Ehsan Naruei Shadfar Davoodi Aliakbar Aghaz Mohammad Mehrad |
| author_facet | Amirhossein Sheykhinasab Amir Ali Mohseni Arash Barahooie Bahari Ehsan Naruei Shadfar Davoodi Aliakbar Aghaz Mohammad Mehrad |
| author_sort | Amirhossein Sheykhinasab |
| collection | DOAJ |
| description | Abstract Permeability is an important parameter in the petrophysical study of a reservoir and serves as a key tool in the development of an oilfield. This is while its prediction, especially in carbonate reservoirs with their relatively lower levels of permeability compared to sandstone reservoirs, is a complicated task as it has larger contributions from heterogeneously distributed vugs and fractures. In this respect, the present research uses the data from two wells (well A for modeling and well B for assessing the generalizability of the developed models) drilled into a carbonate reservoir to estimate the permeability using composite formulations based on least square support vector machine (LSSVM) and multilayer extreme learning machine (MELM) coupled with the so-called cuckoo optimization algorithm (COA), particle swarm optimization (PSO), and genetic algorithm (GA). We further used simple forms of convolutional neural network (CNN) and LSSVM for the sake of comparison. To this end, firstly, the Tukey method was applied to identify and remove the outliers from modeling data. In the next step, the second version of the nondominated sorting genetic algorithm (NSGA-II) was applied to the training data (70% of the entire dataset, selected randomly) to select an optimal group of features that most affect the permeability. The results indicated that although including more input parameters in the modeling added to the resultant coefficient of determination (R 2) while reducing the error successively, yet the slope of the latter reduction got much slow as the number of input parameters exceeded 4. In this respect, petrophysical logs of P-wave travel time, bulk density, neutron porosity, and formation resistivity were identified as the most effective parameters for estimating the permeability. Evaluation of the results of permeability modeling based on root-mean-square error (RMSE) and R 2 shed light on the MELM-COA as the best-performing model in the training and testing stages, as indicated by (RMSE = 0.5600 mD, R 2 = 0.9931) and (RMSE = 0.6019 mD, R 2 = 0.9919), respectively. The generalizability assessment conducted on the prediction of permeability in well B confirmed the MELM-COA can provide reliable permeability predictions by achieving an RMSE of 0.9219 mD. Consequently, the mentioned methodology is strongly recommended for predicting the permeability with high accuracy in similar depth intervals at other wells in the same field should the required dataset be available. |
| first_indexed | 2024-04-09T23:09:50Z |
| format | Article |
| id | doaj.art-8c6c3197e9714e7890181643ff05e905 |
| institution | Directory Open Access Journal |
| issn | 2190-0558 2190-0566 |
| language | English |
| last_indexed | 2024-04-09T23:09:50Z |
| publishDate | 2022-12-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Petroleum Exploration and Production Technology |
| spelling | doaj.art-8c6c3197e9714e7890181643ff05e9052023-03-22T10:29:41ZengSpringerOpenJournal of Petroleum Exploration and Production Technology2190-05582190-05662022-12-0113266168910.1007/s13202-022-01593-zPrediction of permeability of highly heterogeneous hydrocarbon reservoir from conventional petrophysical logs using optimized data-driven algorithmsAmirhossein Sheykhinasab0Amir Ali Mohseni1Arash Barahooie Bahari2Ehsan Naruei3Shadfar Davoodi4Aliakbar Aghaz5Mohammad Mehrad6ACECR Institute of Higher Education (Isfahan Branch)Department of Oil & Chemical Engineering, Science and Research Branch, Islamic Azad UniversityPetroleum Engineering Department, Lamerd Higher Education CenterPetroleum Engineering Department, Lamerd Higher Education CenterSchool of Earth Sciences & Engineering, Tomsk Polytechnic UniversityFaculty of Oil and Gas Engineering, Sahand Oil and Gas Research Institute, Sahand University of TechnologyFaculty of Mining, Petroleum and Geophysics Engineering, Shahrood University of TechnologyAbstract Permeability is an important parameter in the petrophysical study of a reservoir and serves as a key tool in the development of an oilfield. This is while its prediction, especially in carbonate reservoirs with their relatively lower levels of permeability compared to sandstone reservoirs, is a complicated task as it has larger contributions from heterogeneously distributed vugs and fractures. In this respect, the present research uses the data from two wells (well A for modeling and well B for assessing the generalizability of the developed models) drilled into a carbonate reservoir to estimate the permeability using composite formulations based on least square support vector machine (LSSVM) and multilayer extreme learning machine (MELM) coupled with the so-called cuckoo optimization algorithm (COA), particle swarm optimization (PSO), and genetic algorithm (GA). We further used simple forms of convolutional neural network (CNN) and LSSVM for the sake of comparison. To this end, firstly, the Tukey method was applied to identify and remove the outliers from modeling data. In the next step, the second version of the nondominated sorting genetic algorithm (NSGA-II) was applied to the training data (70% of the entire dataset, selected randomly) to select an optimal group of features that most affect the permeability. The results indicated that although including more input parameters in the modeling added to the resultant coefficient of determination (R 2) while reducing the error successively, yet the slope of the latter reduction got much slow as the number of input parameters exceeded 4. In this respect, petrophysical logs of P-wave travel time, bulk density, neutron porosity, and formation resistivity were identified as the most effective parameters for estimating the permeability. Evaluation of the results of permeability modeling based on root-mean-square error (RMSE) and R 2 shed light on the MELM-COA as the best-performing model in the training and testing stages, as indicated by (RMSE = 0.5600 mD, R 2 = 0.9931) and (RMSE = 0.6019 mD, R 2 = 0.9919), respectively. The generalizability assessment conducted on the prediction of permeability in well B confirmed the MELM-COA can provide reliable permeability predictions by achieving an RMSE of 0.9219 mD. Consequently, the mentioned methodology is strongly recommended for predicting the permeability with high accuracy in similar depth intervals at other wells in the same field should the required dataset be available.https://doi.org/10.1007/s13202-022-01593-zPrediction of permeabilityHeterogeneous carbonate reservoirHybrid prediction modelMetaheuristic optimization algorithmDeep learning |
| spellingShingle | Amirhossein Sheykhinasab Amir Ali Mohseni Arash Barahooie Bahari Ehsan Naruei Shadfar Davoodi Aliakbar Aghaz Mohammad Mehrad Prediction of permeability of highly heterogeneous hydrocarbon reservoir from conventional petrophysical logs using optimized data-driven algorithms Journal of Petroleum Exploration and Production Technology Prediction of permeability Heterogeneous carbonate reservoir Hybrid prediction model Metaheuristic optimization algorithm Deep learning |
| title | Prediction of permeability of highly heterogeneous hydrocarbon reservoir from conventional petrophysical logs using optimized data-driven algorithms |
| title_full | Prediction of permeability of highly heterogeneous hydrocarbon reservoir from conventional petrophysical logs using optimized data-driven algorithms |
| title_fullStr | Prediction of permeability of highly heterogeneous hydrocarbon reservoir from conventional petrophysical logs using optimized data-driven algorithms |
| title_full_unstemmed | Prediction of permeability of highly heterogeneous hydrocarbon reservoir from conventional petrophysical logs using optimized data-driven algorithms |
| title_short | Prediction of permeability of highly heterogeneous hydrocarbon reservoir from conventional petrophysical logs using optimized data-driven algorithms |
| title_sort | prediction of permeability of highly heterogeneous hydrocarbon reservoir from conventional petrophysical logs using optimized data driven algorithms |
| topic | Prediction of permeability Heterogeneous carbonate reservoir Hybrid prediction model Metaheuristic optimization algorithm Deep learning |
| url | https://doi.org/10.1007/s13202-022-01593-z |
| work_keys_str_mv | AT amirhosseinsheykhinasab predictionofpermeabilityofhighlyheterogeneoushydrocarbonreservoirfromconventionalpetrophysicallogsusingoptimizeddatadrivenalgorithms AT amiralimohseni predictionofpermeabilityofhighlyheterogeneoushydrocarbonreservoirfromconventionalpetrophysicallogsusingoptimizeddatadrivenalgorithms AT arashbarahooiebahari predictionofpermeabilityofhighlyheterogeneoushydrocarbonreservoirfromconventionalpetrophysicallogsusingoptimizeddatadrivenalgorithms AT ehsannaruei predictionofpermeabilityofhighlyheterogeneoushydrocarbonreservoirfromconventionalpetrophysicallogsusingoptimizeddatadrivenalgorithms AT shadfardavoodi predictionofpermeabilityofhighlyheterogeneoushydrocarbonreservoirfromconventionalpetrophysicallogsusingoptimizeddatadrivenalgorithms AT aliakbaraghaz predictionofpermeabilityofhighlyheterogeneoushydrocarbonreservoirfromconventionalpetrophysicallogsusingoptimizeddatadrivenalgorithms AT mohammadmehrad predictionofpermeabilityofhighlyheterogeneoushydrocarbonreservoirfromconventionalpetrophysicallogsusingoptimizeddatadrivenalgorithms |