A Novel Stacking Heterogeneous Ensemble Model with Hybrid Wrapper-Based Feature Selection for Reservoir Productivity Predictions. (8th January 2021)

• Record Type: Journal Article
• Authors: Zhou, Changlin; Zhou, Lang; Liu, Fei; Chen, Weihua; Wang, Qian; Liang, Keliang; Guo, Wenqiu; Zhou, Liying
• Other Names: Uddin M. Irfan Academic Editor.
• Is Part Of: Complexity. Volume 2021(2021)
• Publication Date: 2021-01-08
• Subjects: Chaotic behavior in systems -- Periodicals; Complexity (Philosophy) -- Periodicals; 003
• DOI: 10.1155/2021/6675638
• Languages: English
• ISSNs: 1076-2787

Abstract

Abstract : Acid fracturing is the most important stimulation method in the carbonate reservoir. Due to the high cost and high risk of acid fracturing, it is necessary to predict the reservoir productivity before acid fracturing, which can provide support to optimize the parameters of acid fracturing. However, the productivity of a single well is affected by various construction parameters and geological conditions. Overfitting can occur when performing productivity prediction tasks on the high-dimension, small-sized reservoir, and acid fracturing dataset. Therefore, this study developed a stacking heterogeneous ensemble model with a hybrid wrapper-based feature selection strategy to forecast reservoir productivity, resolve the overfitting problem, and improve productivity prediction. Compared to other baseline models, the proposed model was found to have the best predictive performances on the test set and effectively deal with the overfitting. The results proved that the hybrid wrapper-based feature selection strategy introduced in this study reduced data acquisition costs and improved model comprehensibility without reducing model performance.