TY  - JOUR
AU  - Zhou, Fangfang
AU  - Wang, Jing
AU  - Yan, Rongfang
AU  - Zhang, Jiandong
PY  - 2026
DA  - 2026/10/25
TI  - Slope Stability Analysis Based on Machine Learning Optimized with Sparrow Search
JO  - ICCK Transactions on Systems Safety and Reliability
T2  - ICCK Transactions on Systems Safety and Reliability
JF  - ICCK Transactions on Systems Safety and Reliability
VL  - 2
IS  - 4
SP  - 235
EP  - 249
DO  - 10.62762/TSSR.2026.749493
UR  - https://www.icck.org/article/abs/TSSR.2026.749493
KW  - Slope stability prediction
KW  - Machine learning
KW  - Intelligent optimization algorithms
KW  - SSA-RF
AB  - Slope stability prediction is a critical challenge in geotechnical engineering. This challenge arises from the complex nonlinear interactions among multiple influencing factors such as soil properties, slope geometry, and hydraulic conditions. Traditional analytical methods rely on simplified assumptions that fail to capture these complex relationships. To address these limitations, this study proposes a hybrid predictive framework that integrates machine learning models with intelligent optimization algorithms. Six key parameters, including unit weight, cohesion, internal friction angle, slope angle, slope height, and pore water pressure ratio, are selected as input features. Three machine learning models, namely Random Forest, XGBoost, and Support Vector Machine, are optimized using four intelligent optimization algorithms, including the Sparrow Search Algorithm, Lion Swarm Optimization, Whale Optimization Algorithm, and Genetic Algorithm, resulting in twelve combined configurations. Among all combinations, the Sparrow Search Algorithm-optimized Random Forest model achieves the best performance, with an accuracy of 95.56%, precision of 95.24%, recall of 95.24%, F1 score of 95.24%, and AUC value of 0.9850. Validation using ten independent engineering cases confirms that the predictions of this model are consistent with actual slope conditions, demonstrating strong engineering applicability. This study provides a systematic comparative framework for hybrid model selection and offers practical guidance for intelligent slope stability assessment.
SN  - 3069-1087
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Zhou2026Slope,
  author = {Fangfang Zhou and Jing Wang and Rongfang Yan and Jiandong Zhang},
  title = {Slope Stability Analysis Based on Machine Learning Optimized with Sparrow Search},
  journal = {ICCK Transactions on Systems Safety and Reliability},
  year = {2026},
  volume = {2},
  number = {4},
  pages = {235-249},
  doi = {10.62762/TSSR.2026.749493},
  url = {https://www.icck.org/article/abs/TSSR.2026.749493},
  abstract = {Slope stability prediction is a critical challenge in geotechnical engineering. This challenge arises from the complex nonlinear interactions among multiple influencing factors such as soil properties, slope geometry, and hydraulic conditions. Traditional analytical methods rely on simplified assumptions that fail to capture these complex relationships. To address these limitations, this study proposes a hybrid predictive framework that integrates machine learning models with intelligent optimization algorithms. Six key parameters, including unit weight, cohesion, internal friction angle, slope angle, slope height, and pore water pressure ratio, are selected as input features. Three machine learning models, namely Random Forest, XGBoost, and Support Vector Machine, are optimized using four intelligent optimization algorithms, including the Sparrow Search Algorithm, Lion Swarm Optimization, Whale Optimization Algorithm, and Genetic Algorithm, resulting in twelve combined configurations. Among all combinations, the Sparrow Search Algorithm-optimized Random Forest model achieves the best performance, with an accuracy of 95.56\%, precision of 95.24\%, recall of 95.24\%, F1 score of 95.24\%, and AUC value of 0.9850. Validation using ten independent engineering cases confirms that the predictions of this model are consistent with actual slope conditions, demonstrating strong engineering applicability. This study provides a systematic comparative framework for hybrid model selection and offers practical guidance for intelligent slope stability assessment.},
  keywords = {Slope stability prediction, Machine learning, Intelligent optimization algorithms, SSA-RF},
  issn = {3069-1087},
  publisher = {Institute of Central Computation and Knowledge}
}