Machine Learning Algorithms for Lithofacies Classification of the Gulong Shale from the Songliao Basin, China
Lithofacies identification and classification are critical for characterizing the hydrocarbon potential of unconventional resources. Although extensive applications of machine learning models in predicting lithofacies have been applied to conventional reservoir systems, the effectiveness of machine...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/6/2581 |
| _version_ | 1797612152045961216 |
|---|---|
| author | Mingqiu Hou Yuxiang Xiao Zhengdong Lei Zhi Yang Yihuai Lou Yuming Liu |
| author_facet | Mingqiu Hou Yuxiang Xiao Zhengdong Lei Zhi Yang Yihuai Lou Yuming Liu |
| author_sort | Mingqiu Hou |
| collection | DOAJ |
| description | Lithofacies identification and classification are critical for characterizing the hydrocarbon potential of unconventional resources. Although extensive applications of machine learning models in predicting lithofacies have been applied to conventional reservoir systems, the effectiveness of machine learning models in predicting clay-rich, lacustrine shale lithofacies has yet to be tackled. Here, we apply machine learning models to conventional well log data to automatically identify the shale lithofacies of Gulong Shale in the Songliao Basin. The shale lithofacies were classified into six types based on total organic carbon and mineral composition data from core analysis and geochemical logs. We compared the accuracy of Multilayer Perceptron (MLP), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Random Forest models. We mitigated the bias of imbalanced data by applying oversampling algorithms. Our results show that ensemble methods (XGBoost and Random Forest) have a better performance in shale lithofacies identification than the other models do, with accuracies of 0.868 and 0.884, respectively. The organic siliceous shale proposed to have the best hydrocarbon potential in Gulong Shale can be identified with F1 scores of 0.853 by XGBoost and 0.877 by Random Forest. Our study suggests that ensemble machine learning models can effectively identify the lithofacies of clay-rich shale from conventional well logs, providing insight into the sweet spot prediction of unconventional reservoirs. Further improvements in model performances can be achieved by adding domain knowledge and employing advanced well log data. |
| first_indexed | 2024-03-11T06:38:18Z |
| format | Article |
| id | doaj.art-e8e881ca5a9a48089da3e0f46dd02afb |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T06:38:18Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-e8e881ca5a9a48089da3e0f46dd02afb2023-11-17T10:48:05ZengMDPI AGEnergies1996-10732023-03-01166258110.3390/en16062581Machine Learning Algorithms for Lithofacies Classification of the Gulong Shale from the Songliao Basin, ChinaMingqiu Hou0Yuxiang Xiao1Zhengdong Lei2Zhi Yang3Yihuai Lou4Yuming Liu5Research Institute of Petroleum Exploration and Development, PetroChina, Beijing 100083, ChinaResearch Institute of Petroleum Exploration and Development, PetroChina, Beijing 100083, ChinaResearch Institute of Petroleum Exploration and Development, PetroChina, Beijing 100083, ChinaResearch Institute of Petroleum Exploration and Development, PetroChina, Beijing 100083, ChinaCenter for Hypergravity Experimental and Interdisciplinary Research, Zhejiang University, Hangzhou 310058, ChinaCollege of Geosciences, China University of Petroleum, Beijing 102249, ChinaLithofacies identification and classification are critical for characterizing the hydrocarbon potential of unconventional resources. Although extensive applications of machine learning models in predicting lithofacies have been applied to conventional reservoir systems, the effectiveness of machine learning models in predicting clay-rich, lacustrine shale lithofacies has yet to be tackled. Here, we apply machine learning models to conventional well log data to automatically identify the shale lithofacies of Gulong Shale in the Songliao Basin. The shale lithofacies were classified into six types based on total organic carbon and mineral composition data from core analysis and geochemical logs. We compared the accuracy of Multilayer Perceptron (MLP), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Random Forest models. We mitigated the bias of imbalanced data by applying oversampling algorithms. Our results show that ensemble methods (XGBoost and Random Forest) have a better performance in shale lithofacies identification than the other models do, with accuracies of 0.868 and 0.884, respectively. The organic siliceous shale proposed to have the best hydrocarbon potential in Gulong Shale can be identified with F1 scores of 0.853 by XGBoost and 0.877 by Random Forest. Our study suggests that ensemble machine learning models can effectively identify the lithofacies of clay-rich shale from conventional well logs, providing insight into the sweet spot prediction of unconventional reservoirs. Further improvements in model performances can be achieved by adding domain knowledge and employing advanced well log data.https://www.mdpi.com/1996-1073/16/6/2581machine learning modelsensemble methodsXGBoostrandom forestshale lithofacieswell log |
| spellingShingle | Mingqiu Hou Yuxiang Xiao Zhengdong Lei Zhi Yang Yihuai Lou Yuming Liu Machine Learning Algorithms for Lithofacies Classification of the Gulong Shale from the Songliao Basin, China Energies machine learning models ensemble methods XGBoost random forest shale lithofacies well log |
| title | Machine Learning Algorithms for Lithofacies Classification of the Gulong Shale from the Songliao Basin, China |
| title_full | Machine Learning Algorithms for Lithofacies Classification of the Gulong Shale from the Songliao Basin, China |
| title_fullStr | Machine Learning Algorithms for Lithofacies Classification of the Gulong Shale from the Songliao Basin, China |
| title_full_unstemmed | Machine Learning Algorithms for Lithofacies Classification of the Gulong Shale from the Songliao Basin, China |
| title_short | Machine Learning Algorithms for Lithofacies Classification of the Gulong Shale from the Songliao Basin, China |
| title_sort | machine learning algorithms for lithofacies classification of the gulong shale from the songliao basin china |
| topic | machine learning models ensemble methods XGBoost random forest shale lithofacies well log |
| url | https://www.mdpi.com/1996-1073/16/6/2581 |
| work_keys_str_mv | AT mingqiuhou machinelearningalgorithmsforlithofaciesclassificationofthegulongshalefromthesongliaobasinchina AT yuxiangxiao machinelearningalgorithmsforlithofaciesclassificationofthegulongshalefromthesongliaobasinchina AT zhengdonglei machinelearningalgorithmsforlithofaciesclassificationofthegulongshalefromthesongliaobasinchina AT zhiyang machinelearningalgorithmsforlithofaciesclassificationofthegulongshalefromthesongliaobasinchina AT yihuailou machinelearningalgorithmsforlithofaciesclassificationofthegulongshalefromthesongliaobasinchina AT yumingliu machinelearningalgorithmsforlithofaciesclassificationofthegulongshalefromthesongliaobasinchina |