@article{ZHAO2025, 
author = {Beichen ZHAO and Yuedong YAO and Jin SHU and Xiaoqi YUAN and Jingyu HOU and Kexin YUE and Xin CHEN},
title = {Intelligent warning model of CO2 gas channeling timing based on deep transfer learning strategy},
year = {2025},
journal = {Petroleum Science Bulletin},
volume = {10},
number = {5},
pages = {1015-1029},
keywords = {CO2 enhanced oil recovery, Stacking model, CO2 gas channeling, deep transfer learning strategy},
url = {https://www.sciopen.com/article/10.3969/j.issn.2096-1693.2025.02.025},
doi = {10.3969/j.issn.2096-1693.2025.02.025},
abstract = {CO2 flooding is a key technology for achieving the dual objectives of efficient reservoir development and carbon sequestration. However, the occurrence of CO2 channeling during the flooding process has emerged as a critical engineering challenge, severely restricting improvements in oil recovery and compromising the safety and efficiency of carbon storage. The Accurate prediction of CO2 channeling onset, coupled with the timely deployment of effective mitigation strategies, is indispensable for safeguarding the economic benefits of CO2 flooding, ensuring the long-term integrity of carbon storage, maximizing incremental oil recovery, and minimizing the operational and environmental risks associated with premature gas channeling. Despite its importance, existing prediction methods face several practical challenges: (1) conventional quantitative characterization models rely heavily on specific reservoir parameters, limiting their applicability to diverse reservoir conditions; (2) in the early stages prior to channeling onset, the gas–oil ratio is close to zero, with the available data typically high-dimensional, small-sample, and sparse-features that hinder empirical formula-based methods from effectively capturing complex nonlinear patterns; (3) high-permeability zones and fractures, which form preferential flow channels, are randomly distributed within the reservoir, exhibit permeability far exceeding that of the matrix, and are difficult to characterize accurately, thereby exacerbating the complexity and uncertainty of CO2 channeling prediction. To address these challenges, this work proposes an intelligent prediction framework that integrates multi-source domain deep transfer learning with a Stacking ensemble learning strategy. A multi-source heterogeneous data training approach is employed to enable adaptive knowledge transfer across reservoirs. Four base learners-Support Vector Regression, Decision Tree, Random Forest, and K-Nearest Neighbors—are incorporated into the Stacking ensemble model, leveraging their complementary prediction strengths to improve fitting performance and enhance the accuracy of complex pattern recognition in the high-dimensional, small-sample datasets associated with CO2 channeling onset prediction. Field application results demonstrate the method’s outstanding predictive performance, achieving a coefficient of determination (R2) of 0.96, mean squared error (MSE) of 12.61, and mean absolute percentage error (MAPE) as low as 6.04%. This work not only provides a more precise and intelligent technical pathway for CO2 channeling prediction but also exhibits strong generalizability and cross-reservoir adaptability. It offers a new solution for optimizing CO2 flooding across different reservoir types, with significant engineering value for enhancing oil recovery, reducing development risks, and achieving largescale carbon sequestration goals. Furthermore, the proposed approach offers valuable methodological insights and transferable principles for the prediction and mitigation of other fluid channeling timing, including gas channeling and water channeling.}
}