Prediction of High-Pressure Physical Properties of Crude Oil Using Explainable Machine Learning Models
High-pressure physical property parameters of formation crude oil are crucial for oilfield exploration, development, and production. Various prediction models have been developed using PVT experimental methods, empirical formulas, regression analysis, and machine learning techniques. However, these...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10815941/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841542577349722112 |
|---|---|
| author | Yawen He Jianwen Chen Zhiyu Wu Yaxin Dun Guichao Du Mengsen Feng Yifan Lu Wei Dang |
| author_facet | Yawen He Jianwen Chen Zhiyu Wu Yaxin Dun Guichao Du Mengsen Feng Yifan Lu Wei Dang |
| author_sort | Yawen He |
| collection | DOAJ |
| description | High-pressure physical property parameters of formation crude oil are crucial for oilfield exploration, development, and production. Various prediction models have been developed using PVT experimental methods, empirical formulas, regression analysis, and machine learning techniques. However, these models often lack sufficient transparency and clarity in their computational processes, limiting their effectiveness in oil and gas exploration and development. This paper employs the Extreme Gradient Boosting (XGBoost) machine learning algorithm, utilizing experimental data such as formation pressure, formation temperature, surface crude oil density, natural gas relative density, gas-oil ratio, saturation pressure, volume factor, formation crude oil density, and formation crude oil viscosity as the dataset. The machine learning model is trained with these parameters to develop the XGBoost prediction model. Optimal parameters, including gas-oil ratio, saturation pressure, volume factor, formation crude oil density, and formation crude oil viscosity, are selected, and the Particle Swarm Optimization (PSO) algorithm is applied to further optimize the model, resulting in the PSO-XGBoost prediction model. To enhance the understanding of the model’s operation and the influencing factors, Shapley Additive Explanations (SHAP) and Explainable Boosting Machine (EBM) techniques are employed for both local and global interpretations of the machine learning model. This study identifies key factors and their weights in predicting high-pressure physical property parameters of formation crude oil, providing valuable insights for predicting shale oil reservoir parameters and enhancing exploration and development efficiency. |
| format | Article |
| id | doaj-art-b5fc6f50c4c941ca83f7232c5f21093f |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-b5fc6f50c4c941ca83f7232c5f21093f2025-01-14T00:01:07ZengIEEEIEEE Access2169-35362025-01-01134912493110.1109/ACCESS.2024.352259510815941Prediction of High-Pressure Physical Properties of Crude Oil Using Explainable Machine Learning ModelsYawen He0Jianwen Chen1Zhiyu Wu2Yaxin Dun3Guichao Du4Mengsen Feng5Yifan Lu6Wei Dang7https://orcid.org/0000-0001-5264-2185Department of Geology, Northwest University, Xi’an, ChinaNo. 12 Oil Production Plant, PetroChina Changqing Oilfield Company, Heshui, ChinaDepartment of Geology, Northwest University, Xi’an, ChinaNo. 12 Oil Production Plant, PetroChina Changqing Oilfield Company, Heshui, ChinaSchool of Earth Sciences and Engineering, Xi’an Shiyou University, Xi’an, ChinaNo. 12 Oil Production Plant, PetroChina Changqing Oilfield Company, Heshui, ChinaNo. 12 Oil Production Plant, PetroChina Changqing Oilfield Company, Heshui, ChinaSchool of Earth Sciences and Engineering, Xi’an Shiyou University, Xi’an, ChinaHigh-pressure physical property parameters of formation crude oil are crucial for oilfield exploration, development, and production. Various prediction models have been developed using PVT experimental methods, empirical formulas, regression analysis, and machine learning techniques. However, these models often lack sufficient transparency and clarity in their computational processes, limiting their effectiveness in oil and gas exploration and development. This paper employs the Extreme Gradient Boosting (XGBoost) machine learning algorithm, utilizing experimental data such as formation pressure, formation temperature, surface crude oil density, natural gas relative density, gas-oil ratio, saturation pressure, volume factor, formation crude oil density, and formation crude oil viscosity as the dataset. The machine learning model is trained with these parameters to develop the XGBoost prediction model. Optimal parameters, including gas-oil ratio, saturation pressure, volume factor, formation crude oil density, and formation crude oil viscosity, are selected, and the Particle Swarm Optimization (PSO) algorithm is applied to further optimize the model, resulting in the PSO-XGBoost prediction model. To enhance the understanding of the model’s operation and the influencing factors, Shapley Additive Explanations (SHAP) and Explainable Boosting Machine (EBM) techniques are employed for both local and global interpretations of the machine learning model. This study identifies key factors and their weights in predicting high-pressure physical property parameters of formation crude oil, providing valuable insights for predicting shale oil reservoir parameters and enhancing exploration and development efficiency.https://ieeexplore.ieee.org/document/10815941/Extreme gradient boostingparticle swarm optimizationmodel interpretationmachine learningPVT property |
| spellingShingle | Yawen He Jianwen Chen Zhiyu Wu Yaxin Dun Guichao Du Mengsen Feng Yifan Lu Wei Dang Prediction of High-Pressure Physical Properties of Crude Oil Using Explainable Machine Learning Models IEEE Access Extreme gradient boosting particle swarm optimization model interpretation machine learning PVT property |
| title | Prediction of High-Pressure Physical Properties of Crude Oil Using Explainable Machine Learning Models |
| title_full | Prediction of High-Pressure Physical Properties of Crude Oil Using Explainable Machine Learning Models |
| title_fullStr | Prediction of High-Pressure Physical Properties of Crude Oil Using Explainable Machine Learning Models |
| title_full_unstemmed | Prediction of High-Pressure Physical Properties of Crude Oil Using Explainable Machine Learning Models |
| title_short | Prediction of High-Pressure Physical Properties of Crude Oil Using Explainable Machine Learning Models |
| title_sort | prediction of high pressure physical properties of crude oil using explainable machine learning models |
| topic | Extreme gradient boosting particle swarm optimization model interpretation machine learning PVT property |
| url | https://ieeexplore.ieee.org/document/10815941/ |
| work_keys_str_mv | AT yawenhe predictionofhighpressurephysicalpropertiesofcrudeoilusingexplainablemachinelearningmodels AT jianwenchen predictionofhighpressurephysicalpropertiesofcrudeoilusingexplainablemachinelearningmodels AT zhiyuwu predictionofhighpressurephysicalpropertiesofcrudeoilusingexplainablemachinelearningmodels AT yaxindun predictionofhighpressurephysicalpropertiesofcrudeoilusingexplainablemachinelearningmodels AT guichaodu predictionofhighpressurephysicalpropertiesofcrudeoilusingexplainablemachinelearningmodels AT mengsenfeng predictionofhighpressurephysicalpropertiesofcrudeoilusingexplainablemachinelearningmodels AT yifanlu predictionofhighpressurephysicalpropertiesofcrudeoilusingexplainablemachinelearningmodels AT weidang predictionofhighpressurephysicalpropertiesofcrudeoilusingexplainablemachinelearningmodels |