Novel regression framework with activation function: unraveling complex slope deformation mechanism

The regression analysis method is a crucial approach for analyzing the slope deformation. To overcome the limitations of conventional methods in capturing the abrupt slope deformation features, a novel regression framework with activation function is established. A reservoir bank slope located in the upper reaches of the Lancang River, Yunnan Province, China, is selected as the case study. The slope deformation characteristic is investigated based on GNSS (global navigation satellite system) monitoring data, especially the dominant factor contributing to deformation resulting from water impoundment. The regression analysis shows an excellent correlation (R=0.99) between regression and measured displacements, confirming that the proposed multifactor regression model with the activation function effectively captures the deformation characteristics of the slope. It is demonstrated that the sliding component, primarily driven by the third water impoundment, has the greatest impact on deformation. The landslide mechanism may involve progressive creep deformation due to increased pore water pressure and reduced shear strength at the slope toe during the first two impoundment stages, bringing the slope to a critical state. The third impoundment intensified deformation, triggering gravity-driven sliding. Continuous sliding recompacted the sliding surface, gradually restoring frictional strength and stabilizing the slope.