Improving corrosion depth estimation in buried pipelines using SMOTE-integrated machine and deep learning models

Abstract

Accurate prediction of corrosion depth in buried pipelines is essential for integrity assessment, reducing inspection and maintenance costs, and managing risk in pipeline transportation systems. Although machine learning (ML) and deep learning (DL) techniques have been widely applied to corrosion prediction, their reliability depends strongly on the quality, representativeness, and balance of the training data. In many previous studies, data imbalance has remained a key limitation, leading to biased models that mainly learn the majority class, underestimate severe corrosion cases, and exhibit reduced overall performance. In this study, a polynomial-based Synthetic Minority Over-sampling Technique (SMOTE) is employed as a data-level solution to alleviate class imbalance and improve model learning. SMOTE is integrated with several predictive models, including a deep learning neural network (DLNN), eXtreme Gradient Boosting (XGBoost), support vector regression (SVR), and multiple linear regression (MLR). The models are developed and evaluated using both the original and the SMOTE-oversampled datasets, and their performance is compared using several statistical metrics. The results show that incorporating SMOTE significantly enhances the predictive capability and robustness of the ML and DL models, attaining a significant reduction of 24.94% in root mean square error (RMSE) compared with the corresponding models trained without SMOTE. The DLNN-SMOTE model provides the best performance, achieving a lower RMSE (0.624) and a higher correlation coefficient (R = 0.940) than other models. These findings demonstrate that SMOTE-enhanced AI models offer an efficient and cost-effective framework for corrosion depth prediction and support more reliable and sustainable integrity management of buried pipelines.