Lithology Identification Method for Sandstone and Mudstone Based on the ADASYN-IRMO-CatBoost Combined Model

Xinyu Wang

doi:10.54691/ytazc190

Authors

Xinyu Wang

DOI:

https://doi.org/10.54691/ytazc190

Keywords:

Lithology Identification; Logging Curves; Sample Imbalance; LightGBM Model; IRMO Algorithm.

Abstract

Accurate lithology identification is a crucial prerequisite for sedimentary environment analysis, oil and gas exploration, and development. Traditional identification methods have problems such as low efficiency, high cost, or limited applicability. This paper proposes an ADASYN-IRMO-CatBoost combined model. Firstly, the ADASYN algorithm is used to perform adaptive sampling on the logging datasets of three wells in the southern Ordos Basin to solve the problem of data imbalance. Then, the Improved Radial Movement Optimization (IRMO) algorithm is utilized to optimize the hyperparameters of the CatBoost model. Finally, CatBoost is used as the core classifier for lithology identification. Experimental results show that the overall accuracy of the combined model on the test set reaches 92%, which is 13% higher than that of the single CatBoost model. The F1 scores of various lithologies and the AUC values of the ROC curves are significantly better than those of the single model, demonstrating stronger classification performance and robustness. It provides an efficient and accurate new method for lithology identification of sandstone and mudstone reservoirs and has good application prospects in the field of geological exploration.

Downloads

Download data is not yet available.

References

[1] Zhao Y, Guan Y, Li P, et al. Reservoir lithology identification based on quantum-derived vortex algorithm and T-S fuzzy reasoning model [J]. Petroleum Geophysical Exploration, 2024, 59(01): 23–30.

[2] Li J, Qian L, Qian L, et al. Multi-attribute basement lithology prediction and effect based on rock classification analysis [J]. Petroleum Geophysical Exploration, 2022, 57(S2): 70–73+227.

[3] Li C, Jia J, Shen A, et al. A new method and application of identifying microbial carbonate lithofacies based on conventional logging [J]. Progress in Geophysics, 2020, 35(05): 1792–1802.

[4] Cheng C, Li P, Chen Y, et al. Research progress on reservoir logging evaluation based on machine learning [J]. Progress in Geophysics, 2022, 37(01): 164–177.

[5] An P, Cao D. Research and application of logging lithology identification method based on deep learning [J]. Progress in Geophysics, 2018, 33(03): 1029–1034.

[6] Hu H, Zeng H, Liang H, et al. Lithology identification method based on principal component analysis and learning vectorized neural network [J]. Well Logging Technology, 2015, 39(05): 586–590.

[7] Chen Y, Wang P. Establishment of three-dimensional solid model of blasting rock mass based on intelligent lithology identification [J]. Coal Geology & Exploration, 2022, 52(04): 92–97.

[8] Xu T, Ren Q, Li J, et al. Analysis of frequent congestion causes based on ADASYN-Optuna-CatBoost and SHAP interpretation algorithm [J]. Highway, 2025, 70(08): 228–239.

[9] Jin L, Luo C, Wei J, et al. Reservoir slope stability analysis under dynamic fluctuating water level using improved radial movement optimisation (IRMO) algorithm [J]. Mathematics, 2024, 12(13): 2055.

[10] Wang J, Wang H, Zhang W, et al. Study on surface subsidence prediction model based on IRMO–XGBoost [J/OL]. Journal of Safety and Environment, 2025: 1–12 [2025-07-28].