An interpretable rockburst prediction model based on SSA-CatBoost

Rockburst is a common geological hazard in deep geotechnical engineering. In this study, the categorical boosting (CatBoost) was used to classify rockburst intensity, and the weight and threshold parameters of CatBoost was optimized by the sparrow search algorithm (SSA). Then, a database containing...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Tunnelling and underground space technology Ročník 164; s. 106820
Hlavní autoři: Kong, Weiqiu, Hou, Peng, Liang, Xin, Gao, Feng, Liu, Quansheng
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.10.2025
Témata:
Intelligent algorithms
Rockburst
SHAP
SSA-CatBoost model
Database
Rockburst
SHAP
SSA-CatBoost model
Intelligent algorithms
ISSN:0886-7798
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Rockburst is a common geological hazard in deep geotechnical engineering. In this study, the categorical boosting (CatBoost) was used to classify rockburst intensity, and the weight and threshold parameters of CatBoost was optimized by the sparrow search algorithm (SSA). Then, a database containing 357 rockburst cases from engineering projects around the world was established, and six features was selected as inputs for the model: the maximum tangential stress of rock σθ; the uniaxial compressive strength of rock σc; the tensile strength of rock σt; the stress ratio of rock σθ/σc; the brittleness ratio of rock σc/σt; and the elastic strain energy index of rock Wet. In the performance test of SSA-CatBoost, it reached an accuracy of 92.96% on the independent test set, and the prediction accuracy was improved by 16.04 percentage points compared to CatBoost. The SSA-CatBoost has better accuracy and generalization capabilities when compared to the existing rockburst empirical criteria and other machine learning models. The accuracy of the SSA-CatBoost reached 100% when the model was validated in three actual projects. In addition, interpretability analysis was conducted on the output results of the SSA-CatBoost model by the shapley additive explanations (SHAP). The input feature Wet that has the greatest impact on the model was identified, and the facilitating or inhibiting effects of different features on the output results are revealed. Research results indicate that the model can predict the levels of rockburst in geotechnical engineering.
ISSN:0886-7798
DOI:10.1016/j.tust.2025.106820