Ensemble Learning for Predicting TOC from Well-Logs of the Unconventional Goldwyer Shale
Precise estimation of total organic carbon (TOC) is extremely important for the successful characterization of an unconventional shale reservoir. Indirect traditional continuous TOC prediction methods from well-logs fail to provide accurate TOC in complex and heterogeneous shale reservoirs. A workfl...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/1/216 |
| _version_ | 1797499197395566592 |
|---|---|
| author | Partha Pratim Mandal Reza Rezaee Irina Emelyanova |
| author_facet | Partha Pratim Mandal Reza Rezaee Irina Emelyanova |
| author_sort | Partha Pratim Mandal |
| collection | DOAJ |
| description | Precise estimation of total organic carbon (TOC) is extremely important for the successful characterization of an unconventional shale reservoir. Indirect traditional continuous TOC prediction methods from well-logs fail to provide accurate TOC in complex and heterogeneous shale reservoirs. A workflow is proposed to predict a continuous TOC profile from well-logs through various ensemble learning regression models in the Goldwyer shale formation of the Canning Basin, WA. A total of 283 TOC data points from ten wells is available from the Rock-Eval analysis of the core specimen where each sample point contains three to five petrophysical logs. The core TOC varies largely, ranging from 0.16 wt % to 4.47 wt % with an average of 1.20 wt %. In addition to the conventional MLR method, four supervised machine learning methods, i.e., ANN, RF, SVM, and GB are trained, validated, and tested for continuous TOC prediction using the ensemble learning approach. To ensure robust TOC prediction, an aggregated model predictor is designed by combining the four ensemble-based models. The model achieved estimation accuracy with R<sup>2</sup> value of 87%. Careful data preparation and feature selection, reconstruction of corrupted or missing logs, and the ensemble learning implementation and optimization have improved TOC prediction accuracy significantly compared to a single model approach. |
| first_indexed | 2024-03-10T03:43:59Z |
| format | Article |
| id | doaj.art-f13edd5588e143bf91e14c5ef47e6520 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T03:43:59Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-f13edd5588e143bf91e14c5ef47e65202023-11-23T11:27:17ZengMDPI AGEnergies1996-10732021-12-0115121610.3390/en15010216Ensemble Learning for Predicting TOC from Well-Logs of the Unconventional Goldwyer ShalePartha Pratim Mandal0Reza Rezaee1Irina Emelyanova2Western Australia School of Mines: Minerals, Energy and Chemical Engineering, Curtin University, Perth, WA 6151, AustraliaWestern Australia School of Mines: Minerals, Energy and Chemical Engineering, Curtin University, Perth, WA 6151, AustraliaCSIRO Energy, Geoscience Data Analytics, Perth, WA 6151, AustraliaPrecise estimation of total organic carbon (TOC) is extremely important for the successful characterization of an unconventional shale reservoir. Indirect traditional continuous TOC prediction methods from well-logs fail to provide accurate TOC in complex and heterogeneous shale reservoirs. A workflow is proposed to predict a continuous TOC profile from well-logs through various ensemble learning regression models in the Goldwyer shale formation of the Canning Basin, WA. A total of 283 TOC data points from ten wells is available from the Rock-Eval analysis of the core specimen where each sample point contains three to five petrophysical logs. The core TOC varies largely, ranging from 0.16 wt % to 4.47 wt % with an average of 1.20 wt %. In addition to the conventional MLR method, four supervised machine learning methods, i.e., ANN, RF, SVM, and GB are trained, validated, and tested for continuous TOC prediction using the ensemble learning approach. To ensure robust TOC prediction, an aggregated model predictor is designed by combining the four ensemble-based models. The model achieved estimation accuracy with R<sup>2</sup> value of 87%. Careful data preparation and feature selection, reconstruction of corrupted or missing logs, and the ensemble learning implementation and optimization have improved TOC prediction accuracy significantly compared to a single model approach.https://www.mdpi.com/1996-1073/15/1/216TOCGoldwyer shalewell-logsensemble learningcanning basin |
| spellingShingle | Partha Pratim Mandal Reza Rezaee Irina Emelyanova Ensemble Learning for Predicting TOC from Well-Logs of the Unconventional Goldwyer Shale Energies TOC Goldwyer shale well-logs ensemble learning canning basin |
| title | Ensemble Learning for Predicting TOC from Well-Logs of the Unconventional Goldwyer Shale |
| title_full | Ensemble Learning for Predicting TOC from Well-Logs of the Unconventional Goldwyer Shale |
| title_fullStr | Ensemble Learning for Predicting TOC from Well-Logs of the Unconventional Goldwyer Shale |
| title_full_unstemmed | Ensemble Learning for Predicting TOC from Well-Logs of the Unconventional Goldwyer Shale |
| title_short | Ensemble Learning for Predicting TOC from Well-Logs of the Unconventional Goldwyer Shale |
| title_sort | ensemble learning for predicting toc from well logs of the unconventional goldwyer shale |
| topic | TOC Goldwyer shale well-logs ensemble learning canning basin |
| url | https://www.mdpi.com/1996-1073/15/1/216 |
| work_keys_str_mv | AT parthapratimmandal ensemblelearningforpredictingtocfromwelllogsoftheunconventionalgoldwyershale AT rezarezaee ensemblelearningforpredictingtocfromwelllogsoftheunconventionalgoldwyershale AT irinaemelyanova ensemblelearningforpredictingtocfromwelllogsoftheunconventionalgoldwyershale |