Method and application of stability prediction model for rock slope

Abstract Slope instability is a prevalent dynamic disaster encountered in the construction of geotechnical engineering projects. Intelligent detection and early warning systems serve as crucial measures for preventing and controlling slope instability. To accurately and efficiently predict the stabi...

Full description

Saved in:
Bibliographic Details
Main Authors: Yun Qi, Chenhao Bai, Xuping Li, Hongfei Duan, Wei Wang, Qingjie Qi
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-01988-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704236064964608
author Yun Qi
Chenhao Bai
Xuping Li
Hongfei Duan
Wei Wang
Qingjie Qi
author_facet Yun Qi
Chenhao Bai
Xuping Li
Hongfei Duan
Wei Wang
Qingjie Qi
author_sort Yun Qi
collection DOAJ
description Abstract Slope instability is a prevalent dynamic disaster encountered in the construction of geotechnical engineering projects. Intelligent detection and early warning systems serve as crucial measures for preventing and controlling slope instability. To accurately and efficiently predict the stability state of slopes, we propose a combined model that integrates the Newton–Raphson optimization algorithm (NRBO) with an optimized extreme gradient boosting tree (XGBoost). Firstly, the primary factors influencing slope instability are thoroughly analyzed. The sample outline is standardized utilizing polar deviation, and the distribution of sample classes is balanced through the application of the Synthetic Minority Over-sampling Technique (SMOTE). Secondly, the XGBoost model is optimized by fine-tuning parameters such as maximum depth (max_depth), learning rate (learning_rate), subsample rate, column sampling rate (colsample-bytree), and minimum loss (gamma) through NRBO. The stability of the model was assessed using a ten fold cross validation method, while the prediction results were comprehensively evaluated utilizing metrics including accuracy (Acc), precision (Pre), recall (Rec), F1 score (Fs), and Cohen’s Kappa coefficient (Ka). Finally, the SHAP additive interpretation method is employed to elucidate the significance and contributions of features influencing the XGBoost model. This model is subsequently applied to ten specific engineering case studies. The results show that after NRBO optimization, the optimal values for the maximum depth, learning rate, subsample proportion, column sample proportion, and minimum loss of the XGBoost model are 7, 0.8247, 0.6326, 0.6263, and 0.0758, respectively. Based on the SHAP model analysis, the main factors influencing the stability of the slopes are g, c, φ, H, and j.
format Article
id doaj-art-847cf45cb17a4751bc92a7513a56bbf2
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-847cf45cb17a4751bc92a7513a56bbf22025-08-20T03:16:50ZengNature PortfolioScientific Reports2045-23222025-05-0115111610.1038/s41598-025-01988-yMethod and application of stability prediction model for rock slopeYun Qi0Chenhao Bai1Xuping Li2Hongfei Duan3Wei Wang4Qingjie Qi5School of Mining and Coal, Inner Mongolia University of Science and TechnologyCollege of Coal Engineering, Shanxi Datong UniversitySchool of Mining and Coal, Inner Mongolia University of Science and TechnologySchool of Civil Engineering, Sun Yat-sen UniversitySchool of Mining and Coal, Inner Mongolia University of Science and TechnologyCollege of Automotive and Mechanical Engineering, Liaoning Institute of Science and EngineeringAbstract Slope instability is a prevalent dynamic disaster encountered in the construction of geotechnical engineering projects. Intelligent detection and early warning systems serve as crucial measures for preventing and controlling slope instability. To accurately and efficiently predict the stability state of slopes, we propose a combined model that integrates the Newton–Raphson optimization algorithm (NRBO) with an optimized extreme gradient boosting tree (XGBoost). Firstly, the primary factors influencing slope instability are thoroughly analyzed. The sample outline is standardized utilizing polar deviation, and the distribution of sample classes is balanced through the application of the Synthetic Minority Over-sampling Technique (SMOTE). Secondly, the XGBoost model is optimized by fine-tuning parameters such as maximum depth (max_depth), learning rate (learning_rate), subsample rate, column sampling rate (colsample-bytree), and minimum loss (gamma) through NRBO. The stability of the model was assessed using a ten fold cross validation method, while the prediction results were comprehensively evaluated utilizing metrics including accuracy (Acc), precision (Pre), recall (Rec), F1 score (Fs), and Cohen’s Kappa coefficient (Ka). Finally, the SHAP additive interpretation method is employed to elucidate the significance and contributions of features influencing the XGBoost model. This model is subsequently applied to ten specific engineering case studies. The results show that after NRBO optimization, the optimal values for the maximum depth, learning rate, subsample proportion, column sample proportion, and minimum loss of the XGBoost model are 7, 0.8247, 0.6326, 0.6263, and 0.0758, respectively. Based on the SHAP model analysis, the main factors influencing the stability of the slopes are g, c, φ, H, and j.https://doi.org/10.1038/s41598-025-01988-ySlope stabilityNewton raphson based optimizer (NRBO)eXtreme gradient boosting (XGBoost)Synthetic minority oversampling technique (SMOTE)Shapley additive explanations (SHAP)
spellingShingle Yun Qi
Chenhao Bai
Xuping Li
Hongfei Duan
Wei Wang
Qingjie Qi
Method and application of stability prediction model for rock slope
Scientific Reports
Slope stability
Newton raphson based optimizer (NRBO)
eXtreme gradient boosting (XGBoost)
Synthetic minority oversampling technique (SMOTE)
Shapley additive explanations (SHAP)
title Method and application of stability prediction model for rock slope
title_full Method and application of stability prediction model for rock slope
title_fullStr Method and application of stability prediction model for rock slope
title_full_unstemmed Method and application of stability prediction model for rock slope
title_short Method and application of stability prediction model for rock slope
title_sort method and application of stability prediction model for rock slope
topic Slope stability
Newton raphson based optimizer (NRBO)
eXtreme gradient boosting (XGBoost)
Synthetic minority oversampling technique (SMOTE)
Shapley additive explanations (SHAP)
url https://doi.org/10.1038/s41598-025-01988-y
work_keys_str_mv AT yunqi methodandapplicationofstabilitypredictionmodelforrockslope
AT chenhaobai methodandapplicationofstabilitypredictionmodelforrockslope
AT xupingli methodandapplicationofstabilitypredictionmodelforrockslope
AT hongfeiduan methodandapplicationofstabilitypredictionmodelforrockslope
AT weiwang methodandapplicationofstabilitypredictionmodelforrockslope
AT qingjieqi methodandapplicationofstabilitypredictionmodelforrockslope