@article{Li2025, 
author = {Juan Li and Mandella Ali M. Fargalla and Wei Yan and Zi-Xu Zhang and Wei Zhang and Zi-Chen Zou and Tang Qing and Tao Yang and Chao-Dong Tan and Guang-Cong Li},
title = {A novel fusion of interpretable boosting algorithm and feature selection for predicting casing damage},
year = {2025},
journal = {Petroleum Science},
volume = {22},
number = {10},
pages = {4157-4173},
keywords = {Casing damage, Machine learning, Feature selection, Sand production, Boosting algorithm},
url = {https://www.sciopen.com/article/10.1016/j.petsci.2025.08.011},
doi = {10.1016/j.petsci.2025.08.011},
abstract = {Casing damage resulting from sand production in unconsolidated sandstone reservoirs can significantly impact the average production of oil wells. However, the prediction task remains challenging due to the complex damage mechanism caused by sand production. This paper presents an innovative approach that combines feature selection (FS) with boosting algorithms to accurately predict casing damage in unconsolidated sandstone reservoirs. A novel TriScore FS technique is developed, combining mRMR, Random Forest, and F-test. The approach integrates three distinct feature selection approaches—TriScore, wrapper, and hybrid TriScore-wrapper and four interpretable Boosting models (AdaBoost, XGBoost, LightGBM, CatBoost). Moreover, shapley additive explanations (SHAP) was used to identify the most significant features across engineering, geological, and production features. The CatBoost model, using the Hybrid TriScore-rapper G1G2 FS method, showed exceptional performance in analyzing data from the Gangxi Oilfield. It achieved the highestaccuracy (95.5%) and recall rate (89.7%) compared to other tested models. Casing service time, casing wall thickness, and perforation density were selected as the top three most important features. This framework enhances predictive robustness and is an effective tool for policymakers and energy analysts, confirming its capability to deliver reliable casing damage forecasts.}
}