Interpretable Predictive Modeling of Tight Gas Well Productivity with SHAP and LIME Techniques
Accurately predicting well productivity is crucial for optimizing gas production and maximizing recovery from tight gas reservoirs. Machine learning (ML) techniques have been applied to build predictive models for the well productivity, but their high complexity and low interpretability can hinder t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/9/3653 |
| _version_ | 1797602669528875008 |
|---|---|
| author | Xianlin Ma Mengyao Hou Jie Zhan Zhenzhi Liu |
| author_facet | Xianlin Ma Mengyao Hou Jie Zhan Zhenzhi Liu |
| author_sort | Xianlin Ma |
| collection | DOAJ |
| description | Accurately predicting well productivity is crucial for optimizing gas production and maximizing recovery from tight gas reservoirs. Machine learning (ML) techniques have been applied to build predictive models for the well productivity, but their high complexity and low interpretability can hinder their practical application. This study proposes using interpretable ML solutions, SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), to provide explicit explanations of the ML prediction model. The study uses data from the Eastern Sulige tight gas field in the Ordos Basin, China, containing various geological and engineering factors. The results show that the gradient boosting decision tree model exhibits superior predictive performance compared to other ML models. The global interpretation using SHAP provides insights into the overall impact of these factors, while the local interpretation using SHAP and LIME offers individualized explanations of well productivity predictions. These results can facilitate improvements in well operations and field development planning, providing a better understanding of the underlying physical processes and supporting more informed and effective decision-making. Ultimately, this study demonstrates the potential of interpretable ML solutions to address the challenges of forecasting well productivity in tight gas reservoirs and enable more efficient and sustainable gas production. |
| first_indexed | 2024-03-11T04:19:52Z |
| format | Article |
| id | doaj.art-2092586974104e54b9acb700c82468f9 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T04:19:52Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-2092586974104e54b9acb700c82468f92023-11-17T22:49:55ZengMDPI AGEnergies1996-10732023-04-01169365310.3390/en16093653Interpretable Predictive Modeling of Tight Gas Well Productivity with SHAP and LIME TechniquesXianlin Ma0Mengyao Hou1Jie Zhan2Zhenzhi Liu3College of Petroleum Engineering, Xi’an Shiyou University, Xi’an 710065, ChinaCollege of Petroleum Engineering, Xi’an Shiyou University, Xi’an 710065, ChinaCollege of Petroleum Engineering, Xi’an Shiyou University, Xi’an 710065, ChinaCollege of Petroleum Engineering, Xi’an Shiyou University, Xi’an 710065, ChinaAccurately predicting well productivity is crucial for optimizing gas production and maximizing recovery from tight gas reservoirs. Machine learning (ML) techniques have been applied to build predictive models for the well productivity, but their high complexity and low interpretability can hinder their practical application. This study proposes using interpretable ML solutions, SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), to provide explicit explanations of the ML prediction model. The study uses data from the Eastern Sulige tight gas field in the Ordos Basin, China, containing various geological and engineering factors. The results show that the gradient boosting decision tree model exhibits superior predictive performance compared to other ML models. The global interpretation using SHAP provides insights into the overall impact of these factors, while the local interpretation using SHAP and LIME offers individualized explanations of well productivity predictions. These results can facilitate improvements in well operations and field development planning, providing a better understanding of the underlying physical processes and supporting more informed and effective decision-making. Ultimately, this study demonstrates the potential of interpretable ML solutions to address the challenges of forecasting well productivity in tight gas reservoirs and enable more efficient and sustainable gas production.https://www.mdpi.com/1996-1073/16/9/3653well productivitymachine learninginterpretabilitySHAPLIME |
| spellingShingle | Xianlin Ma Mengyao Hou Jie Zhan Zhenzhi Liu Interpretable Predictive Modeling of Tight Gas Well Productivity with SHAP and LIME Techniques Energies well productivity machine learning interpretability SHAP LIME |
| title | Interpretable Predictive Modeling of Tight Gas Well Productivity with SHAP and LIME Techniques |
| title_full | Interpretable Predictive Modeling of Tight Gas Well Productivity with SHAP and LIME Techniques |
| title_fullStr | Interpretable Predictive Modeling of Tight Gas Well Productivity with SHAP and LIME Techniques |
| title_full_unstemmed | Interpretable Predictive Modeling of Tight Gas Well Productivity with SHAP and LIME Techniques |
| title_short | Interpretable Predictive Modeling of Tight Gas Well Productivity with SHAP and LIME Techniques |
| title_sort | interpretable predictive modeling of tight gas well productivity with shap and lime techniques |
| topic | well productivity machine learning interpretability SHAP LIME |
| url | https://www.mdpi.com/1996-1073/16/9/3653 |
| work_keys_str_mv | AT xianlinma interpretablepredictivemodelingoftightgaswellproductivitywithshapandlimetechniques AT mengyaohou interpretablepredictivemodelingoftightgaswellproductivitywithshapandlimetechniques AT jiezhan interpretablepredictivemodelingoftightgaswellproductivitywithshapandlimetechniques AT zhenzhiliu interpretablepredictivemodelingoftightgaswellproductivitywithshapandlimetechniques |