Hybrid Machine Learning for Modeling the Relative Permeability Changes in Carbonate Reservoirs under Engineered Water Injection
Advanced production methods utilize complex fluid iteration mechanisms to provide benefits in their implementation. However, modeling these effects with efficiency or accuracy is always a challenge. Machine Learning (ML) applications, which are fundamentally data-driven, can play a crucial role in t...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/13/4849 |
| _version_ | 1797591822417002496 |
|---|---|
| author | Leonardo Fonseca Reginato Rafael dos Santos Gioria Marcio Augusto Sampaio |
| author_facet | Leonardo Fonseca Reginato Rafael dos Santos Gioria Marcio Augusto Sampaio |
| author_sort | Leonardo Fonseca Reginato |
| collection | DOAJ |
| description | Advanced production methods utilize complex fluid iteration mechanisms to provide benefits in their implementation. However, modeling these effects with efficiency or accuracy is always a challenge. Machine Learning (ML) applications, which are fundamentally data-driven, can play a crucial role in this context. Therefore, in this study, we applied a Hybrid Machine Learning (HML) solution to predict petrophysical behaviors during Engineered Water Injection (EWI). This hybrid approach utilizes K-Means and Artificial Neural Network algorithms to predict petrophysical behaviors during EWI. In addition, we applied an optimization process to maximize the Net Present Value (NPV) of a case study, and the results demonstrate that the HML approach outperforms conventional methods by increasing oil production (7.3%) while decreasing the amount of water injected and produced (by 28% and 40%, respectively). Even when the injection price is higher, this method remains profitable. Therefore, our study highlights the potential benefits of utilizing HML solutions for predicting petrophysical behaviors during EWI. This approach can significantly improve the accuracy and efficiency of modeling advanced production methods, which may help the profitability of new and mature oil fields. |
| first_indexed | 2024-03-11T01:42:50Z |
| format | Article |
| id | doaj.art-434826e40c8d42198c5fd1eee67d22b0 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T01:42:50Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-434826e40c8d42198c5fd1eee67d22b02023-11-18T16:26:46ZengMDPI AGEnergies1996-10732023-06-011613484910.3390/en16134849Hybrid Machine Learning for Modeling the Relative Permeability Changes in Carbonate Reservoirs under Engineered Water InjectionLeonardo Fonseca Reginato0Rafael dos Santos Gioria1Marcio Augusto Sampaio2Departamento de Engenharia de Minas e de Petróleo, Escola Politécnica da Universidade de São Paulo, São Paulo 05508-010, BrazilDepartamento de Engenharia de Minas e de Petróleo, Escola Politécnica da Universidade de São Paulo, São Paulo 05508-010, BrazilDepartamento de Engenharia de Minas e de Petróleo, Escola Politécnica da Universidade de São Paulo, São Paulo 05508-010, BrazilAdvanced production methods utilize complex fluid iteration mechanisms to provide benefits in their implementation. However, modeling these effects with efficiency or accuracy is always a challenge. Machine Learning (ML) applications, which are fundamentally data-driven, can play a crucial role in this context. Therefore, in this study, we applied a Hybrid Machine Learning (HML) solution to predict petrophysical behaviors during Engineered Water Injection (EWI). This hybrid approach utilizes K-Means and Artificial Neural Network algorithms to predict petrophysical behaviors during EWI. In addition, we applied an optimization process to maximize the Net Present Value (NPV) of a case study, and the results demonstrate that the HML approach outperforms conventional methods by increasing oil production (7.3%) while decreasing the amount of water injected and produced (by 28% and 40%, respectively). Even when the injection price is higher, this method remains profitable. Therefore, our study highlights the potential benefits of utilizing HML solutions for predicting petrophysical behaviors during EWI. This approach can significantly improve the accuracy and efficiency of modeling advanced production methods, which may help the profitability of new and mature oil fields.https://www.mdpi.com/1996-1073/16/13/4849Hybrid Machine LearningEngineered Water Injectionwettability alteration |
| spellingShingle | Leonardo Fonseca Reginato Rafael dos Santos Gioria Marcio Augusto Sampaio Hybrid Machine Learning for Modeling the Relative Permeability Changes in Carbonate Reservoirs under Engineered Water Injection Energies Hybrid Machine Learning Engineered Water Injection wettability alteration |
| title | Hybrid Machine Learning for Modeling the Relative Permeability Changes in Carbonate Reservoirs under Engineered Water Injection |
| title_full | Hybrid Machine Learning for Modeling the Relative Permeability Changes in Carbonate Reservoirs under Engineered Water Injection |
| title_fullStr | Hybrid Machine Learning for Modeling the Relative Permeability Changes in Carbonate Reservoirs under Engineered Water Injection |
| title_full_unstemmed | Hybrid Machine Learning for Modeling the Relative Permeability Changes in Carbonate Reservoirs under Engineered Water Injection |
| title_short | Hybrid Machine Learning for Modeling the Relative Permeability Changes in Carbonate Reservoirs under Engineered Water Injection |
| title_sort | hybrid machine learning for modeling the relative permeability changes in carbonate reservoirs under engineered water injection |
| topic | Hybrid Machine Learning Engineered Water Injection wettability alteration |
| url | https://www.mdpi.com/1996-1073/16/13/4849 |
| work_keys_str_mv | AT leonardofonsecareginato hybridmachinelearningformodelingtherelativepermeabilitychangesincarbonatereservoirsunderengineeredwaterinjection AT rafaeldossantosgioria hybridmachinelearningformodelingtherelativepermeabilitychangesincarbonatereservoirsunderengineeredwaterinjection AT marcioaugustosampaio hybridmachinelearningformodelingtherelativepermeabilitychangesincarbonatereservoirsunderengineeredwaterinjection |