Hydraulic Flow Unit Classification and Prediction Using Machine Learning Techniques: A Case Study from the Nam Con Son Basin, Offshore Vietnam
The test study area is the Miocene reservoir of Nam Con Son Basin, offshore Vietnam. In the study we used unsupervised learning to automatically cluster hydraulic flow units (HU) based on flow zone indicators (FZI) in a core plug dataset. Then we applied supervised learning to predict HU by combinin...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/14/22/7714 |
| _version_ | 1827676707668099072 |
|---|---|
| author | Ha Quang Man Doan Huy Hien Kieu Duy Thong Bui Viet Dung Nguyen Minh Hoa Truong Khac Hoa Nguyen Van Kieu Pham Quy Ngoc |
| author_facet | Ha Quang Man Doan Huy Hien Kieu Duy Thong Bui Viet Dung Nguyen Minh Hoa Truong Khac Hoa Nguyen Van Kieu Pham Quy Ngoc |
| author_sort | Ha Quang Man |
| collection | DOAJ |
| description | The test study area is the Miocene reservoir of Nam Con Son Basin, offshore Vietnam. In the study we used unsupervised learning to automatically cluster hydraulic flow units (HU) based on flow zone indicators (FZI) in a core plug dataset. Then we applied supervised learning to predict HU by combining core and well log data. We tested several machine learning algorithms. In the first phase, we derived hydraulic flow unit clustering of porosity and permeability of core data using unsupervised machine learning methods such as Ward’s, K mean, Self-Organize Map (SOM) and Fuzzy C mean (FCM). Then we applied supervised machine learning methods including Artificial Neural Networks (ANN), Support Vector Machines (SVM), Boosted Tree (BT) and Random Forest (RF). We combined both core and log data to predict HU logs for the full well section of the wells without core data. We used four wells with six logs (GR, DT, NPHI, LLD, LSS and RHOB) and 578 cores from the Miocene reservoir to train, validate and test the data. Our goal was to show that the correct combination of cores and well logs data would provide reservoir engineers with a tool for HU classification and estimation of permeability in a continuous geological profile. Our research showed that machine learning effectively boosts the prediction of permeability, reduces uncertainty in reservoir modeling, and improves project economics. |
| first_indexed | 2024-03-10T05:31:10Z |
| format | Article |
| id | doaj.art-0ef2eb6fec304e209b0431b38c7af3cc |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T05:31:10Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-0ef2eb6fec304e209b0431b38c7af3cc2023-11-22T23:12:21ZengMDPI AGEnergies1996-10732021-11-011422771410.3390/en14227714Hydraulic Flow Unit Classification and Prediction Using Machine Learning Techniques: A Case Study from the Nam Con Son Basin, Offshore VietnamHa Quang Man0Doan Huy Hien1Kieu Duy Thong2Bui Viet Dung3Nguyen Minh Hoa4Truong Khac Hoa5Nguyen Van Kieu6Pham Quy Ngoc7PetroVietnam Exploration Production Corporation, Hanoi 100000, VietnamVietnam Petroleum Institute, Hanoi 100000, VietnamFaculty of Oil and Gas, Hanoi University of Mining and Geology, Hanoi 100000, VietnamVietnam Petroleum Institute, Hanoi 100000, VietnamFaculty of Oil and Gas, Hanoi University of Mining and Geology, Hanoi 100000, VietnamPetroVietnam Exploration Production Corporation, Hanoi 100000, VietnamFaculty of Geology, Geophysics and Environmental Protection, AGH University of Science and Technology, 30-059 Krakow, PolandVietnam Petroleum Institute, Hanoi 100000, VietnamThe test study area is the Miocene reservoir of Nam Con Son Basin, offshore Vietnam. In the study we used unsupervised learning to automatically cluster hydraulic flow units (HU) based on flow zone indicators (FZI) in a core plug dataset. Then we applied supervised learning to predict HU by combining core and well log data. We tested several machine learning algorithms. In the first phase, we derived hydraulic flow unit clustering of porosity and permeability of core data using unsupervised machine learning methods such as Ward’s, K mean, Self-Organize Map (SOM) and Fuzzy C mean (FCM). Then we applied supervised machine learning methods including Artificial Neural Networks (ANN), Support Vector Machines (SVM), Boosted Tree (BT) and Random Forest (RF). We combined both core and log data to predict HU logs for the full well section of the wells without core data. We used four wells with six logs (GR, DT, NPHI, LLD, LSS and RHOB) and 578 cores from the Miocene reservoir to train, validate and test the data. Our goal was to show that the correct combination of cores and well logs data would provide reservoir engineers with a tool for HU classification and estimation of permeability in a continuous geological profile. Our research showed that machine learning effectively boosts the prediction of permeability, reduces uncertainty in reservoir modeling, and improves project economics.https://www.mdpi.com/1996-1073/14/22/7714hydraulic flow unitsmachine learningpermeabilityNam Con Son Basin |
| spellingShingle | Ha Quang Man Doan Huy Hien Kieu Duy Thong Bui Viet Dung Nguyen Minh Hoa Truong Khac Hoa Nguyen Van Kieu Pham Quy Ngoc Hydraulic Flow Unit Classification and Prediction Using Machine Learning Techniques: A Case Study from the Nam Con Son Basin, Offshore Vietnam Energies hydraulic flow units machine learning permeability Nam Con Son Basin |
| title | Hydraulic Flow Unit Classification and Prediction Using Machine Learning Techniques: A Case Study from the Nam Con Son Basin, Offshore Vietnam |
| title_full | Hydraulic Flow Unit Classification and Prediction Using Machine Learning Techniques: A Case Study from the Nam Con Son Basin, Offshore Vietnam |
| title_fullStr | Hydraulic Flow Unit Classification and Prediction Using Machine Learning Techniques: A Case Study from the Nam Con Son Basin, Offshore Vietnam |
| title_full_unstemmed | Hydraulic Flow Unit Classification and Prediction Using Machine Learning Techniques: A Case Study from the Nam Con Son Basin, Offshore Vietnam |
| title_short | Hydraulic Flow Unit Classification and Prediction Using Machine Learning Techniques: A Case Study from the Nam Con Son Basin, Offshore Vietnam |
| title_sort | hydraulic flow unit classification and prediction using machine learning techniques a case study from the nam con son basin offshore vietnam |
| topic | hydraulic flow units machine learning permeability Nam Con Son Basin |
| url | https://www.mdpi.com/1996-1073/14/22/7714 |
| work_keys_str_mv | AT haquangman hydraulicflowunitclassificationandpredictionusingmachinelearningtechniquesacasestudyfromthenamconsonbasinoffshorevietnam AT doanhuyhien hydraulicflowunitclassificationandpredictionusingmachinelearningtechniquesacasestudyfromthenamconsonbasinoffshorevietnam AT kieuduythong hydraulicflowunitclassificationandpredictionusingmachinelearningtechniquesacasestudyfromthenamconsonbasinoffshorevietnam AT buivietdung hydraulicflowunitclassificationandpredictionusingmachinelearningtechniquesacasestudyfromthenamconsonbasinoffshorevietnam AT nguyenminhhoa hydraulicflowunitclassificationandpredictionusingmachinelearningtechniquesacasestudyfromthenamconsonbasinoffshorevietnam AT truongkhachoa hydraulicflowunitclassificationandpredictionusingmachinelearningtechniquesacasestudyfromthenamconsonbasinoffshorevietnam AT nguyenvankieu hydraulicflowunitclassificationandpredictionusingmachinelearningtechniquesacasestudyfromthenamconsonbasinoffshorevietnam AT phamquyngoc hydraulicflowunitclassificationandpredictionusingmachinelearningtechniquesacasestudyfromthenamconsonbasinoffshorevietnam |