Prediction of Safety Factor of Newly Failed Red Clay Slope Based on XGBoost-PSO-SVR Model

Currently, most studies on slope stability either neglect or consider only one of the two critical factors—rainfall conditions and crack state—that influence the stability of newly failed slopes. To address this limitation, the eleven parameters, such as the slope height, internal friction angle, cohesion, rainfall conditions, and crack state were selected as evaluation indexes. GeoStudio software was also used to simulate the slope safety factor under various parameters, and 363 sets of data were obtained. The XGBoost-PSO-SVR (eXtreme Gradient Boosting-Particle Swarm Optimization-Support Vector Regression) model was employed to train the simulation results and construct a predictive model. Compared with the single-machine methods of XGBoost and PSO-SVR, the MSE of XGBoost-PSO-SVR is reduced by 71.9% and 57.8%, respectively. Furthermore, when compared to four single-machine models—Decision Tree (DT), Naive Bayes (NB), Random Forest (RF), and K-Nearest Neighbors (KNN)—the XGBoost-PSO-SVR model demonstrated superior training performance. The predicted safety factor for a newly failed slope in Yongchun County, Fujian Province, during November 4-7, 2016, was 0.9658, which closely aligns with the actual conditions. A new way for the stability prediction of newly failed slope could be provided by this study under various factors, such as rainfall conditions and crack state.