Surrogate-assisted hydraulic fracture optimization workflow with applications for shale gas reservoir development: a comparative study of machine learning models
Unconventional reservoirs have become the main alternative for increasing oil and gas reserves around the world. Owing to their ultralow permeability properties and special pore structure, hydraulic fracturing technology is necessary to realize the efficient development and economic management of un...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2022-06-01
|
| Series: | Natural Gas Industry B |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352854022000262 |
| _version_ | 1797282885532647424 |
|---|---|
| author | Cong Xiao Shicheng Zhang Xinfang Ma Tong Zhou Xuechen Li |
| author_facet | Cong Xiao Shicheng Zhang Xinfang Ma Tong Zhou Xuechen Li |
| author_sort | Cong Xiao |
| collection | DOAJ |
| description | Unconventional reservoirs have become the main alternative for increasing oil and gas reserves around the world. Owing to their ultralow permeability properties and special pore structure, hydraulic fracturing technology is necessary to realize the efficient development and economic management of unconventional resources. To maximize the production capacity of wells, several fracture parameters, including fracture number, length, width, conductivity, and spacing, need to be optimized effectively. The optimization of hydraulic fracture parameters in shale gas reservoirs generally demands intensive computations owing to the necessity of numerous physicalmodel simulations. This study proposes a machine learning (ML)–assisted global optimization framework to rapidly obtain optimal fracture parameters. We employed three supervised ML models, including the radialbasis function, K-nearest neighbor, and multilayer perceptron, to emulate the relationship between fracture parameters and shale gas productivity for multistage fractured horizontal wells. Firstly, several forward shale gas simulations with embedded discrete fracture models generate training samples. Then, the samples are divided into training and testing samples to train these ML models and optimize network hyper parameters, respectively. Finally, the trained ML models are combined with an intelligent differential evolution algorithm to optimize the fracture parameters. This novel method has been applied to a naturally fractured reservoir model based on the real-field Barnett shale formation. The obtained results are compared with those of conventional optimizations with high-fidelity models. The results confirm the superiority of the proposed method owing to its very low computational cost. The use of ML modeling technology and an intelligent optimization algorithm could greatly contribute to simulation optimization and design, prompting progress in the intelligent development of unconventional oil and gas reservoirs in China. |
| first_indexed | 2024-03-07T17:20:58Z |
| format | Article |
| id | doaj.art-41e08312edbf4419804bedf3bb6ac351 |
| institution | Directory Open Access Journal |
| issn | 2352-8540 |
| language | English |
| last_indexed | 2024-03-07T17:20:58Z |
| publishDate | 2022-06-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Natural Gas Industry B |
| spelling | doaj.art-41e08312edbf4419804bedf3bb6ac3512024-03-02T20:09:06ZengKeAi Communications Co., Ltd.Natural Gas Industry B2352-85402022-06-0193219231Surrogate-assisted hydraulic fracture optimization workflow with applications for shale gas reservoir development: a comparative study of machine learning modelsCong Xiao0Shicheng Zhang1Xinfang Ma2Tong Zhou3Xuechen Li4Key Laboratory of Petroleum Engineering, Ministry of Education, China University of Petroleum, Beijing, 102249, China; College of Petroleum Engineering, China University of Petroleum, Beijing, 102249, China; Corresponding author. College of Petroleum Engineering, China University of Petroleum, Beijing, 102249, China.Key Laboratory of Petroleum Engineering, Ministry of Education, China University of Petroleum, Beijing, 102249, China; College of Petroleum Engineering, China University of Petroleum, Beijing, 102249, ChinaKey Laboratory of Petroleum Engineering, Ministry of Education, China University of Petroleum, Beijing, 102249, China; College of Petroleum Engineering, China University of Petroleum, Beijing, 102249, ChinaResearch Institute of Petroleum Exploration and Production, SINOPEC, Beijing 100083, ChinaKey Laboratory of Petroleum Engineering, Ministry of Education, China University of Petroleum, Beijing, 102249, China; College of Petroleum Engineering, China University of Petroleum, Beijing, 102249, ChinaUnconventional reservoirs have become the main alternative for increasing oil and gas reserves around the world. Owing to their ultralow permeability properties and special pore structure, hydraulic fracturing technology is necessary to realize the efficient development and economic management of unconventional resources. To maximize the production capacity of wells, several fracture parameters, including fracture number, length, width, conductivity, and spacing, need to be optimized effectively. The optimization of hydraulic fracture parameters in shale gas reservoirs generally demands intensive computations owing to the necessity of numerous physicalmodel simulations. This study proposes a machine learning (ML)–assisted global optimization framework to rapidly obtain optimal fracture parameters. We employed three supervised ML models, including the radialbasis function, K-nearest neighbor, and multilayer perceptron, to emulate the relationship between fracture parameters and shale gas productivity for multistage fractured horizontal wells. Firstly, several forward shale gas simulations with embedded discrete fracture models generate training samples. Then, the samples are divided into training and testing samples to train these ML models and optimize network hyper parameters, respectively. Finally, the trained ML models are combined with an intelligent differential evolution algorithm to optimize the fracture parameters. This novel method has been applied to a naturally fractured reservoir model based on the real-field Barnett shale formation. The obtained results are compared with those of conventional optimizations with high-fidelity models. The results confirm the superiority of the proposed method owing to its very low computational cost. The use of ML modeling technology and an intelligent optimization algorithm could greatly contribute to simulation optimization and design, prompting progress in the intelligent development of unconventional oil and gas reservoirs in China.http://www.sciencedirect.com/science/article/pii/S2352854022000262Shale gasMulti fractured horizontal wellMachine learning modelingIntelligent optimization |
| spellingShingle | Cong Xiao Shicheng Zhang Xinfang Ma Tong Zhou Xuechen Li Surrogate-assisted hydraulic fracture optimization workflow with applications for shale gas reservoir development: a comparative study of machine learning models Natural Gas Industry B Shale gas Multi fractured horizontal well Machine learning modeling Intelligent optimization |
| title | Surrogate-assisted hydraulic fracture optimization workflow with applications for shale gas reservoir development: a comparative study of machine learning models |
| title_full | Surrogate-assisted hydraulic fracture optimization workflow with applications for shale gas reservoir development: a comparative study of machine learning models |
| title_fullStr | Surrogate-assisted hydraulic fracture optimization workflow with applications for shale gas reservoir development: a comparative study of machine learning models |
| title_full_unstemmed | Surrogate-assisted hydraulic fracture optimization workflow with applications for shale gas reservoir development: a comparative study of machine learning models |
| title_short | Surrogate-assisted hydraulic fracture optimization workflow with applications for shale gas reservoir development: a comparative study of machine learning models |
| title_sort | surrogate assisted hydraulic fracture optimization workflow with applications for shale gas reservoir development a comparative study of machine learning models |
| topic | Shale gas Multi fractured horizontal well Machine learning modeling Intelligent optimization |
| url | http://www.sciencedirect.com/science/article/pii/S2352854022000262 |
| work_keys_str_mv | AT congxiao surrogateassistedhydraulicfractureoptimizationworkflowwithapplicationsforshalegasreservoirdevelopmentacomparativestudyofmachinelearningmodels AT shichengzhang surrogateassistedhydraulicfractureoptimizationworkflowwithapplicationsforshalegasreservoirdevelopmentacomparativestudyofmachinelearningmodels AT xinfangma surrogateassistedhydraulicfractureoptimizationworkflowwithapplicationsforshalegasreservoirdevelopmentacomparativestudyofmachinelearningmodels AT tongzhou surrogateassistedhydraulicfractureoptimizationworkflowwithapplicationsforshalegasreservoirdevelopmentacomparativestudyofmachinelearningmodels AT xuechenli surrogateassistedhydraulicfractureoptimizationworkflowwithapplicationsforshalegasreservoirdevelopmentacomparativestudyofmachinelearningmodels |