Well-Production Forecasting Using Machine Learning with Feature Selection and Automatic Hyperparameter Optimization

Ruibin Zhu, Ning Li, Yongqiang Duan, Gaofeng Li, Guohua Liu, Fengjiao Qu, Changjun Long, Xin Wang, Qinzhuo Liao () and Gensheng Li
Additional contact information
Ruibin Zhu: College of Petroleum Engineering, China University of Petroleum-Beijing, Beijing 102249, China
Ning Li: Research Institute of Oil and Gas Technology, PetroChina Huabei Oilfield Company, Renqiu 062552, China
Yongqiang Duan: Research Institute of Oil and Gas Technology, PetroChina Huabei Oilfield Company, Renqiu 062552, China
Gaofeng Li: Research Institute of Oil and Gas Technology, PetroChina Huabei Oilfield Company, Renqiu 062552, China
Guohua Liu: Research Institute of Oil and Gas Technology, PetroChina Huabei Oilfield Company, Renqiu 062552, China
Fengjiao Qu: Research Institute of Oil and Gas Technology, PetroChina Huabei Oilfield Company, Renqiu 062552, China
Changjun Long: Research Institute of Oil and Gas Technology, PetroChina Huabei Oilfield Company, Renqiu 062552, China
Xin Wang: Research Institute of Oil and Gas Technology, PetroChina Huabei Oilfield Company, Renqiu 062552, China
Qinzhuo Liao: College of Petroleum Engineering, China University of Petroleum-Beijing, Beijing 102249, China
Gensheng Li: College of Petroleum Engineering, China University of Petroleum-Beijing, Beijing 102249, China

Energies, 2024, vol. 18, issue 1, 1-20

Abstract: 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 2 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.

Keywords: machine learning; production forecast; data preprocessing; principal component analysis; AutoGluon (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/1/99/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/1/99/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2024:i:1:p:99-:d:1556259

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().