Well-Production Forecasting Using Machine Learning with Feature Selection and Automatic Hyperparameter Optimization
Well-production forecasting plays a crucial role in oil and gas development. Traditional methods, such as numerical simulations, require substantial computational effort, while empirical models tend to exhibit poor accuracy. To address these issues, machine learning, a widely adopted artificial inte...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/18/1/99 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549253619482624 |
|---|---|
| author | Ruibin Zhu Ning Li Yongqiang Duan Gaofeng Li Guohua Liu Fengjiao Qu Changjun Long Xin Wang Qinzhuo Liao Gensheng Li |
| author_facet | Ruibin Zhu Ning Li Yongqiang Duan Gaofeng Li Guohua Liu Fengjiao Qu Changjun Long Xin Wang Qinzhuo Liao Gensheng Li |
| author_sort | Ruibin Zhu |
| collection | DOAJ |
| description | Well-production forecasting plays a crucial role in oil and gas development. Traditional methods, such as numerical simulations, require substantial computational effort, while empirical models tend to exhibit poor accuracy. To address these issues, machine learning, a widely adopted artificial intelligence approach, is employed to develop production forecasting models in order to enhance the accuracy of oil and gas well-production predictions. This research focuses on the geological, engineering, and production data of 435 fracturing wells in the North China Oilfield. First, outliers were detected, and missing values were handled using the mean imputation and nearest neighbor methods. Subsequently, Pearson correlation coefficients were utilized to eliminate linearly irrelevant features and optimize the dataset. By calculating the gray correlation degrees, maximum mutual information, feature importance, and Shapley additive explanation (SHAP) values, an in-depth analysis of various dominant factors was conducted. To further assess the importance of these factors, the entropy weight method was employed. Ultimately, 19 features that were highly correlated with the target variable were successfully screened as inputs for subsequent models. Based on the AutoGluon framework, model training was conducted using 5-fold cross-validation combined with bagging and stacking techniques. The training results show that the model achieved an R<sup>2</sup> of 0.79 on the training set, indicating good fitting ability. This study offers a promising approach for the development of oil and gas production forecasting models. |
| format | Article |
| id | doaj-art-253aa68fca93491c997a4e46506cb52f |
| institution | Kabale University |
| issn | 1996-1073 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj-art-253aa68fca93491c997a4e46506cb52f2025-01-10T13:17:05ZengMDPI AGEnergies1996-10732024-12-011819910.3390/en18010099Well-Production Forecasting Using Machine Learning with Feature Selection and Automatic Hyperparameter OptimizationRuibin Zhu0Ning Li1Yongqiang Duan2Gaofeng Li3Guohua Liu4Fengjiao Qu5Changjun Long6Xin Wang7Qinzhuo Liao8Gensheng Li9College of Petroleum Engineering, China University of Petroleum-Beijing, Beijing 102249, ChinaResearch Institute of Oil and Gas Technology, PetroChina Huabei Oilfield Company, Renqiu 062552, ChinaResearch Institute of Oil and Gas Technology, PetroChina Huabei Oilfield Company, Renqiu 062552, ChinaResearch Institute of Oil and Gas Technology, PetroChina Huabei Oilfield Company, Renqiu 062552, ChinaResearch Institute of Oil and Gas Technology, PetroChina Huabei Oilfield Company, Renqiu 062552, ChinaResearch Institute of Oil and Gas Technology, PetroChina Huabei Oilfield Company, Renqiu 062552, ChinaResearch Institute of Oil and Gas Technology, PetroChina Huabei Oilfield Company, Renqiu 062552, ChinaResearch Institute of Oil and Gas Technology, PetroChina Huabei Oilfield Company, Renqiu 062552, ChinaCollege of Petroleum Engineering, China University of Petroleum-Beijing, Beijing 102249, ChinaCollege of Petroleum Engineering, China University of Petroleum-Beijing, Beijing 102249, ChinaWell-production forecasting plays a crucial role in oil and gas development. Traditional methods, such as numerical simulations, require substantial computational effort, while empirical models tend to exhibit poor accuracy. To address these issues, machine learning, a widely adopted artificial intelligence approach, is employed to develop production forecasting models in order to enhance the accuracy of oil and gas well-production predictions. This research focuses on the geological, engineering, and production data of 435 fracturing wells in the North China Oilfield. First, outliers were detected, and missing values were handled using the mean imputation and nearest neighbor methods. Subsequently, Pearson correlation coefficients were utilized to eliminate linearly irrelevant features and optimize the dataset. By calculating the gray correlation degrees, maximum mutual information, feature importance, and Shapley additive explanation (SHAP) values, an in-depth analysis of various dominant factors was conducted. To further assess the importance of these factors, the entropy weight method was employed. Ultimately, 19 features that were highly correlated with the target variable were successfully screened as inputs for subsequent models. Based on the AutoGluon framework, model training was conducted using 5-fold cross-validation combined with bagging and stacking techniques. The training results show that the model achieved an R<sup>2</sup> of 0.79 on the training set, indicating good fitting ability. This study offers a promising approach for the development of oil and gas production forecasting models.https://www.mdpi.com/1996-1073/18/1/99machine learningproduction forecastdata preprocessingprincipal component analysisAutoGluon |
| spellingShingle | Ruibin Zhu Ning Li Yongqiang Duan Gaofeng Li Guohua Liu Fengjiao Qu Changjun Long Xin Wang Qinzhuo Liao Gensheng Li Well-Production Forecasting Using Machine Learning with Feature Selection and Automatic Hyperparameter Optimization Energies machine learning production forecast data preprocessing principal component analysis AutoGluon |
| title | Well-Production Forecasting Using Machine Learning with Feature Selection and Automatic Hyperparameter Optimization |
| title_full | Well-Production Forecasting Using Machine Learning with Feature Selection and Automatic Hyperparameter Optimization |
| title_fullStr | Well-Production Forecasting Using Machine Learning with Feature Selection and Automatic Hyperparameter Optimization |
| title_full_unstemmed | Well-Production Forecasting Using Machine Learning with Feature Selection and Automatic Hyperparameter Optimization |
| title_short | Well-Production Forecasting Using Machine Learning with Feature Selection and Automatic Hyperparameter Optimization |
| title_sort | well production forecasting using machine learning with feature selection and automatic hyperparameter optimization |
| topic | machine learning production forecast data preprocessing principal component analysis AutoGluon |
| url | https://www.mdpi.com/1996-1073/18/1/99 |
| work_keys_str_mv | AT ruibinzhu wellproductionforecastingusingmachinelearningwithfeatureselectionandautomatichyperparameteroptimization AT ningli wellproductionforecastingusingmachinelearningwithfeatureselectionandautomatichyperparameteroptimization AT yongqiangduan wellproductionforecastingusingmachinelearningwithfeatureselectionandautomatichyperparameteroptimization AT gaofengli wellproductionforecastingusingmachinelearningwithfeatureselectionandautomatichyperparameteroptimization AT guohualiu wellproductionforecastingusingmachinelearningwithfeatureselectionandautomatichyperparameteroptimization AT fengjiaoqu wellproductionforecastingusingmachinelearningwithfeatureselectionandautomatichyperparameteroptimization AT changjunlong wellproductionforecastingusingmachinelearningwithfeatureselectionandautomatichyperparameteroptimization AT xinwang wellproductionforecastingusingmachinelearningwithfeatureselectionandautomatichyperparameteroptimization AT qinzhuoliao wellproductionforecastingusingmachinelearningwithfeatureselectionandautomatichyperparameteroptimization AT genshengli wellproductionforecastingusingmachinelearningwithfeatureselectionandautomatichyperparameteroptimization |