A Carbonate Rock Identification Method Based on the Interpretability of KS-XGBoost: A Case Study From the Sichuan Basin, SW China
- 19 May 2026
- journal article
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 31 (07) , 4777-4795
Abstract
Summary: Carbonate lithology identification has long posed challenges in petroleum exploration due to overlapping well logging responses caused by compositional similarities and the thin-bedded nature of transitional lithologies. Although machine learning (ML) has provided new approaches to address this issue, the “black-box” nature of most ML models limits their geological interpretability and practical reliability. In this study, a high-precision lithology classification model was applied and coupled with the Shapley additive explanations (SHAP) framework to quantitatively evaluate the contribution and directionality of each logging feature to the model’s predictions. By combining K-means oversampling with the XGBoost algorithm, the training data were effectively balanced, and the robustness of the model was improved, ultimately achieving an overall classification accuracy of 92%. SHAP analysis further clarified the controlling influence of key logging parameters on lithology discrimination, revealing the model’s internal decision logic in a physically meaningful manner. This research establishes an interpretable and data-driven workflow for carbonate lithology identification and provides a theoretical and technical reference for the reliable application of ML in complex carbonate reservoir characterization.Keywords
This publication has 58 references indexed in Scilit:
- Integrating SHAP Explainability in Few-Shot Lithology Identification Using Dynamic Semi-Supervised Meta-LearningNatural Resources Research, 2025
- Enhanced Lithology Classification Using an Interpretable SHAP Model Integrating Semi-Supervised Contrastive Learning and Transformer with Well Logging DataNatural Resources Research, 2025
- Lithology identification method based on integrated K-means clustering and meta-object representationArabian Journal of Geosciences, 2022
- Gradient Boosting Decision Tree for Lithology Identification with Well Logs: A Case Study of Zhaoxian Gold Deposit, Shandong Peninsula, ChinaNatural Resources Research, 2021
- Identification of sedimentary facies with well logs: an indirect approach with multinomial logistic regression and artificial neural networkArabian Journal of Geosciences, 2017
- Origin of dolomite in the Middle Ordovician peritidal platform carbonates in the northern Ordos Basin, western ChinaPetroleum Science, 2016
- Learning from imbalanced data: open challenges and future directionsProgress in Artificial Intelligence, 2016
- Correlation and variable importance in random forestsStatistics and Computing, 2016
- Safe-Level-SMOTE: Safe-Level-Synthetic Minority Over-Sampling TEchnique for Handling the Class Imbalanced Problem2009
- Controls on sonic velocity in carbonatesPure and Applied Geophysics, 1993