Permeability Prediction Using Machine Learning Methods for the CO<sub>2</sub> Injectivity of the Precipice Sandstone in Surat Basin, Australia
This paper presents the results of a research project which investigated permeability prediction for the Precipice Sandstone of the Surat Basin. Machine learning techniques were used for permeability estimation based on multiple wireline logs. This information improves the prediction of CO<sub>...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/6/2053 |
| _version_ | 1797471766816227328 |
|---|---|
| author | Reza Rezaee Jamiu Ekundayo |
| author_facet | Reza Rezaee Jamiu Ekundayo |
| author_sort | Reza Rezaee |
| collection | DOAJ |
| description | This paper presents the results of a research project which investigated permeability prediction for the Precipice Sandstone of the Surat Basin. Machine learning techniques were used for permeability estimation based on multiple wireline logs. This information improves the prediction of CO<sub>2</sub> injectivity in this formation. Well logs and core data were collected from 5 boreholes in the Surat Basin, where extensive core data and complete sets of conventional well logs exist for the Precipice Sandstone. Four different machine learning (ML) techniques, including Random Forest (RF), Artificial neural network (ANN), Gradient Boosting Regressor (GBR), and Support Vector Regressor (SVR), were independently trained with a wide range of hyper-parameters to ensure that not only is the best model selected, but also the right combination of model parameters is selected. Cross-validation for 20 different combinations of the seven available input logs was used for this study. Based on the performances in the validation and blind testing phases, the ANN with all seven logs used as input was found to give the best performance in predicting permeability for the Precipice Sandstone with the coefficient of determination (R<sup>2</sup>) of about 0.93 and 0.87 for the training and blind data sets respectively. Multi-regression analysis also appears to be a successful approach to calculate reservoir permeability for the Precipice Sandstone. Models with a complete set of well logs can generate reservoir permeability with R<sup>2</sup> of more than 90%. |
| first_indexed | 2024-03-09T19:52:45Z |
| format | Article |
| id | doaj.art-02dbea189c8e431ea5f084bc13268e98 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T19:52:45Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-02dbea189c8e431ea5f084bc13268e982023-11-24T01:03:50ZengMDPI AGEnergies1996-10732022-03-01156205310.3390/en15062053Permeability Prediction Using Machine Learning Methods for the CO<sub>2</sub> Injectivity of the Precipice Sandstone in Surat Basin, AustraliaReza Rezaee0Jamiu Ekundayo1Western Australian School of Mines, Minerals, Energy and Chemical Engineering, Curtin University, Perth 6102, AustraliaWestern Australian School of Mines, Minerals, Energy and Chemical Engineering, Curtin University, Perth 6102, AustraliaThis paper presents the results of a research project which investigated permeability prediction for the Precipice Sandstone of the Surat Basin. Machine learning techniques were used for permeability estimation based on multiple wireline logs. This information improves the prediction of CO<sub>2</sub> injectivity in this formation. Well logs and core data were collected from 5 boreholes in the Surat Basin, where extensive core data and complete sets of conventional well logs exist for the Precipice Sandstone. Four different machine learning (ML) techniques, including Random Forest (RF), Artificial neural network (ANN), Gradient Boosting Regressor (GBR), and Support Vector Regressor (SVR), were independently trained with a wide range of hyper-parameters to ensure that not only is the best model selected, but also the right combination of model parameters is selected. Cross-validation for 20 different combinations of the seven available input logs was used for this study. Based on the performances in the validation and blind testing phases, the ANN with all seven logs used as input was found to give the best performance in predicting permeability for the Precipice Sandstone with the coefficient of determination (R<sup>2</sup>) of about 0.93 and 0.87 for the training and blind data sets respectively. Multi-regression analysis also appears to be a successful approach to calculate reservoir permeability for the Precipice Sandstone. Models with a complete set of well logs can generate reservoir permeability with R<sup>2</sup> of more than 90%.https://www.mdpi.com/1996-1073/15/6/2053permeability predictionmachine learningCO<sub>2</sub> injectivityprecipice sandstoneSurat BasinAustralia |
| spellingShingle | Reza Rezaee Jamiu Ekundayo Permeability Prediction Using Machine Learning Methods for the CO<sub>2</sub> Injectivity of the Precipice Sandstone in Surat Basin, Australia Energies permeability prediction machine learning CO<sub>2</sub> injectivity precipice sandstone Surat Basin Australia |
| title | Permeability Prediction Using Machine Learning Methods for the CO<sub>2</sub> Injectivity of the Precipice Sandstone in Surat Basin, Australia |
| title_full | Permeability Prediction Using Machine Learning Methods for the CO<sub>2</sub> Injectivity of the Precipice Sandstone in Surat Basin, Australia |
| title_fullStr | Permeability Prediction Using Machine Learning Methods for the CO<sub>2</sub> Injectivity of the Precipice Sandstone in Surat Basin, Australia |
| title_full_unstemmed | Permeability Prediction Using Machine Learning Methods for the CO<sub>2</sub> Injectivity of the Precipice Sandstone in Surat Basin, Australia |
| title_short | Permeability Prediction Using Machine Learning Methods for the CO<sub>2</sub> Injectivity of the Precipice Sandstone in Surat Basin, Australia |
| title_sort | permeability prediction using machine learning methods for the co sub 2 sub injectivity of the precipice sandstone in surat basin australia |
| topic | permeability prediction machine learning CO<sub>2</sub> injectivity precipice sandstone Surat Basin Australia |
| url | https://www.mdpi.com/1996-1073/15/6/2053 |
| work_keys_str_mv | AT rezarezaee permeabilitypredictionusingmachinelearningmethodsforthecosub2subinjectivityoftheprecipicesandstoneinsuratbasinaustralia AT jamiuekundayo permeabilitypredictionusingmachinelearningmethodsforthecosub2subinjectivityoftheprecipicesandstoneinsuratbasinaustralia |